Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-12-01 20:04:04 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'oobabooga:dev' into dev

Browse Source
This commit is contained in:
Artificiangel 2024-06-12 21:05:35 -04:00 committed by GitHub
commit 98443196d1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
37 changed files with 548 additions and 742 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

272
README.md
View File

@ -11,7 +11,7 @@ Its goal is to become the [AUTOMATIC1111/stable-diffusion-webui](https://github.
## Features ## Features
* 3 interface modes: default (two columns), notebook, and chat. * 3 interface modes: default (two columns), notebook, and chat.
* Multiple model backends: [Transformers](https://github.com/huggingface/transformers), [llama.cpp](https://github.com/ggerganov/llama.cpp) (through [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)), [ExLlamaV2](https://github.com/turboderp/exllamav2), [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ), [AutoAWQ](https://github.com/casper-hansen/AutoAWQ), [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa), [QuIP#](https://github.com/Cornell-RelaxML/quip-sharp). * Multiple model backends: [Transformers](https://github.com/huggingface/transformers), [llama.cpp](https://github.com/ggerganov/llama.cpp) (through [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)), [ExLlamaV2](https://github.com/turboderp/exllamav2), [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ), [AutoAWQ](https://github.com/casper-hansen/AutoAWQ).
* Dropdown menu for quickly switching between different models. * Dropdown menu for quickly switching between different models.
* Large number of extensions (built-in and user-contributed), including Coqui TTS for realistic voice outputs, Whisper STT for voice inputs, translation, [multimodal pipelines](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/multimodal), vector databases, Stable Diffusion integration, and a lot more. See [the wiki](https://github.com/oobabooga/text-generation-webui/wiki/07-%E2%80%90-Extensions) and [the extensions directory](https://github.com/oobabooga/text-generation-webui-extensions) for details. * Large number of extensions (built-in and user-contributed), including Coqui TTS for realistic voice outputs, Whisper STT for voice inputs, translation, [multimodal pipelines](https://github.com/oobabooga/text-generation-webui/tree/main/extensions/multimodal), vector databases, Stable Diffusion integration, and a lot more. See [the wiki](https://github.com/oobabooga/text-generation-webui/wiki/07-%E2%80%90-Extensions) and [the extensions directory](https://github.com/oobabooga/text-generation-webui-extensions) for details.
* [Chat with custom characters](https://github.com/oobabooga/text-generation-webui/wiki/03-%E2%80%90-Parameters-Tab#character). * [Chat with custom characters](https://github.com/oobabooga/text-generation-webui/wiki/03-%E2%80%90-Parameters-Tab#character).
@ -200,168 +200,146 @@ pip install -r <requirements file that you have used> --upgrade
List of command-line flags List of command-line flags
</summary> </summary>
#### Basic settings ```txt
usage: server.py [-h] [--multi-user] [--character CHARACTER] [--model MODEL] [--lora LORA [LORA ...]] [--model-dir MODEL_DIR] [--lora-dir LORA_DIR] [--model-menu] [--settings SETTINGS]
[--extensions EXTENSIONS [EXTENSIONS ...]] [--verbose] [--chat-buttons] [--idle-timeout IDLE_TIMEOUT] [--loader LOADER] [--cpu] [--auto-devices]
[--gpu-memory GPU_MEMORY [GPU_MEMORY ...]] [--cpu-memory CPU_MEMORY] [--disk] [--disk-cache-dir DISK_CACHE_DIR] [--load-in-8bit] [--bf16] [--no-cache] [--trust-remote-code]
[--force-safetensors] [--no_use_fast] [--use_flash_attention_2] [--load-in-4bit] [--use_double_quant] [--compute_dtype COMPUTE_DTYPE] [--quant_type QUANT_TYPE] [--flash-attn]
[--tensorcores] [--n_ctx N_CTX] [--threads THREADS] [--threads-batch THREADS_BATCH] [--no_mul_mat_q] [--n_batch N_BATCH] [--no-mmap] [--mlock] [--n-gpu-layers N_GPU_LAYERS]
[--tensor_split TENSOR_SPLIT] [--numa] [--logits_all] [--no_offload_kqv] [--cache-capacity CACHE_CAPACITY] [--row_split] [--streaming-llm] [--attention-sink-size ATTENTION_SINK_SIZE]
[--gpu-split GPU_SPLIT] [--autosplit] [--max_seq_len MAX_SEQ_LEN] [--cfg-cache] [--no_flash_attn] [--cache_8bit] [--cache_4bit] [--num_experts_per_token NUM_EXPERTS_PER_TOKEN]
[--triton] [--no_inject_fused_mlp] [--no_use_cuda_fp16] [--desc_act] [--disable_exllama] [--disable_exllamav2] [--wbits WBITS] [--groupsize GROUPSIZE] [--no_inject_fused_attention]
[--hqq-backend HQQ_BACKEND] [--deepspeed] [--nvme-offload-dir NVME_OFFLOAD_DIR] [--local_rank LOCAL_RANK] [--alpha_value ALPHA_VALUE] [--rope_freq_base ROPE_FREQ_BASE]
[--compress_pos_emb COMPRESS_POS_EMB] [--listen] [--listen-port LISTEN_PORT] [--listen-host LISTEN_HOST] [--share] [--auto-launch] [--gradio-auth GRADIO_AUTH]
[--gradio-auth-path GRADIO_AUTH_PATH] [--ssl-keyfile SSL_KEYFILE] [--ssl-certfile SSL_CERTFILE] [--api] [--public-api] [--public-api-id PUBLIC_API_ID] [--api-port API_PORT]
[--api-key API_KEY] [--admin-key ADMIN_KEY] [--nowebui] [--multimodal-pipeline MULTIMODAL_PIPELINE] [--model_type MODEL_TYPE] [--pre_layer PRE_LAYER [PRE_LAYER ...]]
[--checkpoint CHECKPOINT] [--monkey-patch]
| Flag | Description | Text generation web UI
|--------------------------------------------|-------------|
| `-h`, `--help` | show this help message and exit |
| `--multi-user` | Multi-user mode. Chat histories are not saved or automatically loaded. WARNING: this is likely not safe for sharing publicly. |
| `--character CHARACTER` | The name of the character to load in chat mode by default. |
| `--model MODEL` | Name of the model to load by default. |
| `--lora LORA [LORA ...]` | The list of LoRAs to load. If you want to load more than one LoRA, write the names separated by spaces. |
| `--model-dir MODEL_DIR` | Path to directory with all the models. |
| `--lora-dir LORA_DIR` | Path to directory with all the loras. |
| `--model-menu` | Show a model menu in the terminal when the web UI is first launched. |
| `--settings SETTINGS_FILE` | Load the default interface settings from this yaml file. See `settings-template.yaml` for an example. If you create a file called `settings.yaml`, this file will be loaded by default without the need to use the `--settings` flag. |
| `--extensions EXTENSIONS [EXTENSIONS ...]` | The list of extensions to load. If you want to load more than one extension, write the names separated by spaces. |
| `--verbose` | Print the prompts to the terminal. |
| `--chat-buttons` | Show buttons on the chat tab instead of a hover menu. |
#### Model loader options:
-h, --help show this help message and exit
| Flag | Description | Basic settings:
|--------------------------------------------|-------------| --multi-user Multi-user mode. Chat histories are not saved or automatically loaded. Warning: this is likely not safe for sharing publicly.
| `--loader LOADER` | Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlamav2_HF, ExLlamav2, AutoGPTQ, AutoAWQ, GPTQ-for-LLaMa, QuIP#. | --character CHARACTER The name of the character to load in chat mode by default.
--model MODEL Name of the model to load by default.
--lora LORA [LORA ...] The list of LoRAs to load. If you want to load more than one LoRA, write the names separated by spaces.
--model-dir MODEL_DIR Path to directory with all the models.
--lora-dir LORA_DIR Path to directory with all the loras.
--model-menu Show a model menu in the terminal when the web UI is first launched.
--settings SETTINGS Load the default interface settings from this yaml file. See settings-template.yaml for an example. If you create a file called settings.yaml, this
file will be loaded by default without the need to use the --settings flag.
--extensions EXTENSIONS [EXTENSIONS ...] The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.
--verbose Print the prompts to the terminal.
--chat-buttons Show buttons on the chat tab instead of a hover menu.
--idle-timeout IDLE_TIMEOUT Unload model after this many minutes of inactivity. It will be automatically reloaded when you try to use it again.
#### Accelerate/transformers Model loader:
--loader LOADER Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlamav2_HF, ExLlamav2,
AutoGPTQ, AutoAWQ.
| Flag | Description | Transformers/Accelerate:
|---------------------------------------------|-------------| --cpu Use the CPU to generate text. Warning: Training on CPU is extremely slow.
| `--cpu` | Use the CPU to generate text. Warning: Training on CPU is extremely slow. | --auto-devices Automatically split the model across the available GPU(s) and CPU.
| `--auto-devices` | Automatically split the model across the available GPU(s) and CPU. | --gpu-memory GPU_MEMORY [GPU_MEMORY ...] Maximum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs. You can also set values
| `--gpu-memory GPU_MEMORY [GPU_MEMORY ...]` | Maximum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs. You can also set values in MiB like --gpu-memory 3500MiB. | in MiB like --gpu-memory 3500MiB.
| `--cpu-memory CPU_MEMORY` | Maximum CPU memory in GiB to allocate for offloaded weights. Same as above. | --cpu-memory CPU_MEMORY Maximum CPU memory in GiB to allocate for offloaded weights. Same as above.
| `--disk` | If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk. | --disk If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.
| `--disk-cache-dir DISK_CACHE_DIR` | Directory to save the disk cache to. Defaults to "cache". | --disk-cache-dir DISK_CACHE_DIR Directory to save the disk cache to. Defaults to "cache".
| `--load-in-8bit` | Load the model with 8-bit precision (using bitsandbytes). | --load-in-8bit Load the model with 8-bit precision (using bitsandbytes).
| `--bf16` | Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU. | --bf16 Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.
| `--no-cache` | Set `use_cache` to `False` while generating text. This reduces VRAM usage slightly, but it comes at a performance cost. | --no-cache Set use_cache to False while generating text. This reduces VRAM usage slightly, but it comes at a performance cost.
| `--trust-remote-code` | Set `trust_remote_code=True` while loading the model. Necessary for some models. | --trust-remote-code Set trust_remote_code=True while loading the model. Necessary for some models.
| `--no_use_fast` | Set use_fast=False while loading the tokenizer (it's True by default). Use this if you have any problems related to use_fast. | --force-safetensors Set use_safetensors=True while loading the model. This prevents arbitrary code execution.
| `--use_flash_attention_2` | Set use_flash_attention_2=True while loading the model. | --no_use_fast Set use_fast=False while loading the tokenizer (it's True by default). Use this if you have any problems related to use_fast.
--use_flash_attention_2 Set use_flash_attention_2=True while loading the model.
#### bitsandbytes 4-bit bitsandbytes 4-bit:
--load-in-4bit Load the model with 4-bit precision (using bitsandbytes).
--use_double_quant use_double_quant for 4-bit.
--compute_dtype COMPUTE_DTYPE compute dtype for 4-bit. Valid options: bfloat16, float16, float32.
--quant_type QUANT_TYPE quant_type for 4-bit. Valid options: nf4, fp4.
⚠️ Requires minimum compute of 7.0 on Windows at the moment. llama.cpp:
--flash-attn Use flash-attention.
--tensorcores Use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards. NVIDIA only.
--n_ctx N_CTX Size of the prompt context.
--threads THREADS Number of threads to use.
--threads-batch THREADS_BATCH Number of threads to use for batches/prompt processing.
--no_mul_mat_q Disable the mulmat kernels.
--n_batch N_BATCH Maximum number of prompt tokens to batch together when calling llama_eval.
--no-mmap Prevent mmap from being used.
--mlock Force the system to keep the model in RAM.
--n-gpu-layers N_GPU_LAYERS Number of layers to offload to the GPU.
--tensor_split TENSOR_SPLIT Split the model across multiple GPUs. Comma-separated list of proportions. Example: 18,17.
--numa Activate NUMA task allocation for llama.cpp.
--logits_all Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.
--no_offload_kqv Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.
--cache-capacity CACHE_CAPACITY Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed.
--row_split Split the model by rows across GPUs. This may improve multi-gpu performance.
--streaming-llm Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.
--attention-sink-size ATTENTION_SINK_SIZE StreamingLLM: number of sink tokens. Only used if the trimmed prompt does not share a prefix with the old prompt.
| Flag | Description | ExLlamaV2:
|---------------------------------------------|-------------| --gpu-split GPU_SPLIT Comma-separated list of VRAM (in GB) to use per GPU device for model layers. Example: 20,7,7.
| `--load-in-4bit` | Load the model with 4-bit precision (using bitsandbytes). | --autosplit Autosplit the model tensors across the available GPUs. This causes --gpu-split to be ignored.
| `--use_double_quant` | use_double_quant for 4-bit. | --max_seq_len MAX_SEQ_LEN Maximum sequence length.
| `--compute_dtype COMPUTE_DTYPE` | compute dtype for 4-bit. Valid options: bfloat16, float16, float32. | --cfg-cache ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.
| `--quant_type QUANT_TYPE` | quant_type for 4-bit. Valid options: nf4, fp4. | --no_flash_attn Force flash-attention to not be used.
--cache_8bit Use 8-bit cache to save VRAM.
--cache_4bit Use Q4 cache to save VRAM.
--num_experts_per_token NUM_EXPERTS_PER_TOKEN Number of experts to use for generation. Applies to MoE models like Mixtral.
#### llama.cpp AutoGPTQ:
--triton Use triton.
--no_inject_fused_mlp Triton mode only: disable the use of fused MLP, which will use less VRAM at the cost of slower inference.
--no_use_cuda_fp16 This can make models faster on some systems.
--desc_act For models that do not have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig.
--disable_exllama Disable ExLlama kernel, which can improve inference speed on some systems.
--disable_exllamav2 Disable ExLlamav2 kernel.
--wbits WBITS Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.
--groupsize GROUPSIZE Group size.
| Flag | Description | AutoAWQ:
|-------------|-------------| --no_inject_fused_attention Disable the use of fused attention, which will use less VRAM at the cost of slower inference.
| `--tensorcores` | Use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards. NVIDIA only. |
| `--flash-attn` | Use flash-attention. |
| `--n_ctx N_CTX` | Size of the prompt context. |
| `--threads` | Number of threads to use. |
| `--threads-batch THREADS_BATCH` | Number of threads to use for batches/prompt processing. |
| `--no_mul_mat_q` | Disable the mulmat kernels. |
| `--n_batch` | Maximum number of prompt tokens to batch together when calling llama_eval. |
| `--no-mmap` | Prevent mmap from being used. |
| `--mlock` | Force the system to keep the model in RAM. |
| `--n-gpu-layers N_GPU_LAYERS` | Number of layers to offload to the GPU. |
| `--tensor_split TENSOR_SPLIT` | Split the model across multiple GPUs. Comma-separated list of proportions. Example: 18,17. |
| `--numa` | Activate NUMA task allocation for llama.cpp. |
| `--logits_all`| Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower. |
| `--no_offload_kqv` | Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance. |
| `--cache-capacity CACHE_CAPACITY` | Maximum cache capacity (llama-cpp-python). Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. |
| `--row_split` | Split the model by rows across GPUs. This may improve multi-gpu performance. |
| `--streaming-llm` | Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed. |
| `--attention-sink-size ATTENTION_SINK_SIZE` | StreamingLLM: number of sink tokens. Only used if the trimmed prompt doesn't share a prefix with the old prompt. |
#### ExLlamav2 HQQ:
--hqq-backend HQQ_BACKEND Backend for the HQQ loader. Valid options: PYTORCH, PYTORCH_COMPILE, ATEN.
| Flag | Description | DeepSpeed:
|------------------|-------------| --deepspeed Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration.
|`--gpu-split` | Comma-separated list of VRAM (in GB) to use per GPU device for model layers. Example: 20,7,7. | --nvme-offload-dir NVME_OFFLOAD_DIR DeepSpeed: Directory to use for ZeRO-3 NVME offloading.
|`--max_seq_len MAX_SEQ_LEN` | Maximum sequence length. | --local_rank LOCAL_RANK DeepSpeed: Optional argument for distributed setups.
|`--cfg-cache` | ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader. |
|`--no_flash_attn` | Force flash-attention to not be used. |
|`--cache_8bit` | Use 8-bit cache to save VRAM. |
|`--cache_4bit` | Use Q4 cache to save VRAM. |
|`--num_experts_per_token NUM_EXPERTS_PER_TOKEN` | Number of experts to use for generation. Applies to MoE models like Mixtral. |
#### AutoGPTQ RoPE:
--alpha_value ALPHA_VALUE Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both.
--rope_freq_base ROPE_FREQ_BASE If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63).
--compress_pos_emb COMPRESS_POS_EMB Positional embeddings compression factor. Should be set to (context length) / (model's original context length). Equal to 1/rope_freq_scale.
| Flag | Description | Gradio:
|------------------|-------------| --listen Make the web UI reachable from your local network.
| `--triton` | Use triton. | --listen-port LISTEN_PORT The listening port that the server will use.
| `--no_inject_fused_attention` | Disable the use of fused attention, which will use less VRAM at the cost of slower inference. | --listen-host LISTEN_HOST The hostname that the server will use.
| `--no_inject_fused_mlp` | Triton mode only: disable the use of fused MLP, which will use less VRAM at the cost of slower inference. | --share Create a public URL. This is useful for running the web UI on Google Colab or similar.
| `--no_use_cuda_fp16` | This can make models faster on some systems. | --auto-launch Open the web UI in the default browser upon launch.
| `--desc_act` | For models that don't have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig. | --gradio-auth GRADIO_AUTH Set Gradio authentication password in the format "username:password". Multiple credentials can also be supplied with "u1:p1,u2:p2,u3:p3".
| `--disable_exllama` | Disable ExLlama kernel, which can improve inference speed on some systems. | --gradio-auth-path GRADIO_AUTH_PATH Set the Gradio authentication file path. The file should contain one or more user:password pairs in the same format as above.
| `--disable_exllamav2` | Disable ExLlamav2 kernel. | --ssl-keyfile SSL_KEYFILE The path to the SSL certificate key file.
--ssl-certfile SSL_CERTFILE The path to the SSL certificate cert file.
#### GPTQ-for-LLaMa API:
--api Enable the API extension.
--public-api Create a public URL for the API using Cloudfare.
--public-api-id PUBLIC_API_ID Tunnel ID for named Cloudflare Tunnel. Use together with public-api option.
--api-port API_PORT The listening port for the API.
--api-key API_KEY API authentication key.
--admin-key ADMIN_KEY API authentication key for admin tasks like loading and unloading models. If not set, will be the same as --api-key.
--nowebui Do not launch the Gradio UI. Useful for launching the API in standalone mode.
| Flag | Description | Multimodal:
|---------------------------|-------------| --multimodal-pipeline MULTIMODAL_PIPELINE The multimodal pipeline to use. Examples: llava-7b, llava-13b.
| `--wbits WBITS` | Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. | ```
| `--model_type MODEL_TYPE` | Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported. |
| `--groupsize GROUPSIZE` | Group size. |
| `--pre_layer PRE_LAYER [PRE_LAYER ...]` | The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models. For multi-gpu, write the numbers separated by spaces, eg `--pre_layer 30 60`. |
| `--checkpoint CHECKPOINT` | The path to the quantized checkpoint file. If not specified, it will be automatically detected. |
| `--monkey-patch` | Apply the monkey patch for using LoRAs with quantized models. |
#### HQQ
| Flag | Description |
|-------------|-------------|
| `--hqq-backend` | Backend for the HQQ loader. Valid options: PYTORCH, PYTORCH_COMPILE, ATEN. |
#### DeepSpeed
| Flag | Description |
|---------------------------------------|-------------|
| `--deepspeed` | Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration. |
| `--nvme-offload-dir NVME_OFFLOAD_DIR` | DeepSpeed: Directory to use for ZeRO-3 NVME offloading. |
| `--local_rank LOCAL_RANK` | DeepSpeed: Optional argument for distributed setups. |
#### RoPE (for llama.cpp, ExLlamaV2, and transformers)
| Flag | Description |
|------------------|-------------|
| `--alpha_value ALPHA_VALUE` | Positional embeddings alpha factor for NTK RoPE scaling. Use either this or `compress_pos_emb`, not both. |
| `--rope_freq_base ROPE_FREQ_BASE` | If greater than 0, will be used instead of alpha_value. Those two are related by `rope_freq_base = 10000 * alpha_value ^ (64 / 63)`. |
| `--compress_pos_emb COMPRESS_POS_EMB` | Positional embeddings compression factor. Should be set to `(context length) / (model's original context length)`. Equal to `1/rope_freq_scale`. |
#### Gradio
| Flag | Description |
|---------------------------------------|-------------|
| `--listen` | Make the web UI reachable from your local network. |
| `--listen-port LISTEN_PORT` | The listening port that the server will use. |
| `--listen-host LISTEN_HOST` | The hostname that the server will use. |
| `--share` | Create a public URL. This is useful for running the web UI on Google Colab or similar. |
| `--auto-launch` | Open the web UI in the default browser upon launch. |
| `--gradio-auth USER:PWD` | Set Gradio authentication password in the format "username:password". Multiple credentials can also be supplied with "u1:p1,u2:p2,u3:p3". |
| `--gradio-auth-path GRADIO_AUTH_PATH` | Set the Gradio authentication file path. The file should contain one or more user:password pairs in the same format as above. |
| `--ssl-keyfile SSL_KEYFILE` | The path to the SSL certificate key file. |
| `--ssl-certfile SSL_CERTFILE` | The path to the SSL certificate cert file. |
#### API
| Flag | Description |
|---------------------------------------|-------------|
| `--api` | Enable the API extension. |
| `--public-api` | Create a public URL for the API using Cloudfare. |
| `--public-api-id PUBLIC_API_ID` | Tunnel ID for named Cloudflare Tunnel. Use together with public-api option. |
| `--api-port API_PORT` | The listening port for the API. |
| `--api-key API_KEY` | API authentication key. |
| `--admin-key ADMIN_KEY` | API authentication key for admin tasks like loading and unloading models. If not set, will be the same as --api-key. |
| `--nowebui` | Do not launch the Gradio UI. Useful for launching the API in standalone mode. |
#### Multimodal
| Flag | Description |
|---------------------------------------|-------------|
| `--multimodal-pipeline PIPELINE` | The multimodal pipeline to use. Examples: `llava-7b`, `llava-13b`. |
</details> </details>

8
docs/04 - Model Tab.md
View File

@ -64,14 +64,6 @@ Loads: GPTQ models.
* **no_use_cuda_fp16**: On some systems, the performance can be very bad with this unset. Can usually be ignored. * **no_use_cuda_fp16**: On some systems, the performance can be very bad with this unset. Can usually be ignored.
* **desc_act**: For ancient models without proper metadata, sets the model "act-order" parameter manually. Can usually be ignored. * **desc_act**: For ancient models without proper metadata, sets the model "act-order" parameter manually. Can usually be ignored.
### GPTQ-for-LLaMa
Loads: GPTQ models.
Ancient loader, the first one to implement 4-bit quantization. It works on older GPUs for which ExLlamaV2 and AutoGPTQ do not work, and it doesn't work with "act-order", so you should use it with simple 4-bit-128g models.
* **pre_layer**: Used for CPU offloading. The higher the number, the more layers will be sent to the GPU. GPTQ-for-LLaMa CPU offloading was faster than the one implemented in AutoGPTQ the last time I checked.
### llama.cpp ### llama.cpp
Loads: GGUF models. Note: GGML models have been deprecated and do not work anymore. Loads: GGUF models. Note: GGML models have been deprecated and do not work anymore.

2
docs/05 - Training Tab.md
View File

@ -124,7 +124,7 @@ When you're running training, the WebUI's console window will log reports that i
"Loss" in the world of AI training theoretically means "how close is the model to perfect", with `0` meaning "absolutely perfect". This is calculated by measuring the difference between the model outputting exactly the text you're training it to output, and what it actually outputs. "Loss" in the world of AI training theoretically means "how close is the model to perfect", with `0` meaning "absolutely perfect". This is calculated by measuring the difference between the model outputting exactly the text you're training it to output, and what it actually outputs.
In practice, a good LLM should have a very complex variable range of ideas running in its artificial head, so a loss of `0` would indicate that the model has broken and forgotten to how think about anything other than what you trained it. In practice, a good LLM should have a very complex variable range of ideas running in its artificial head, so a loss of `0` would indicate that the model has broken and forgotten how to think about anything other than what you trained it on.
So, in effect, Loss is a balancing game: you want to get it low enough that it understands your data, but high enough that it isn't forgetting everything else. Generally, if it goes below `1.0`, it's going to start forgetting its prior memories, and you should stop training. In some cases you may prefer to take it as low as `0.5` (if you want it to be very very predictable). Different goals have different needs, so don't be afraid to experiment and see what works best for you. So, in effect, Loss is a balancing game: you want to get it low enough that it understands your data, but high enough that it isn't forgetting everything else. Generally, if it goes below `1.0`, it's going to start forgetting its prior memories, and you should stop training. In some cases you may prefer to take it as low as `0.5` (if you want it to be very very predictable). Different goals have different needs, so don't be afraid to experiment and see what works best for you.

22
docs/08 - Additional Tips.md
View File

@ -13,28 +13,6 @@ Source: https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/1126
This file will be automatically detected the next time you start the web UI. This file will be automatically detected the next time you start the web UI.
## Using LoRAs with GPTQ-for-LLaMa
This requires using a monkey patch that is supported by this web UI: https://github.com/johnsmith0031/alpaca_lora_4bit
To use it:
Install alpaca_lora_4bit using pip
```
git clone https://github.com/johnsmith0031/alpaca_lora_4bit.git
cd alpaca_lora_4bit
git fetch origin winglian-setup_pip
git checkout winglian-setup_pip
pip install .
```
Start the UI with the --monkey-patch flag:
```
python server.py --model llama-7b-4bit-128g --listen --lora tloen_alpaca-lora-7b --monkey-patch
```
## DeepSpeed ## DeepSpeed
`DeepSpeed ZeRO-3` is an alternative offloading strategy for full-precision (16-bit) transformers models. `DeepSpeed ZeRO-3` is an alternative offloading strategy for full-precision (16-bit) transformers models.

2
docs/09 - Docker.md
View File

@ -19,7 +19,7 @@ Use these commands to launch the image:
``` ```
cd text-generation-webui cd text-generation-webui
ln -s docker/{nvidia/Dockerfile,docker-compose.yml,.dockerignore} . ln -s docker/{nvidia/Dockerfile,nvidia/docker-compose.yml,.dockerignore} .
cp docker/.env.example .env cp docker/.env.example .env
# Edit .env and set TORCH_CUDA_ARCH_LIST based on your GPU model # Edit .env and set TORCH_CUDA_ARCH_LIST based on your GPU model
docker compose up --build docker compose up --build

8
docs/What Works.md
View File

@ -2,15 +2,13 @@
| Loader | Loading 1 LoRA | Loading 2 or more LoRAs | Training LoRAs | Multimodal extension | Perplexity evaluation | | Loader | Loading 1 LoRA | Loading 2 or more LoRAs | Training LoRAs | Multimodal extension | Perplexity evaluation |
|----------------|----------------|-------------------------|----------------|----------------------|-----------------------| |----------------|----------------|-------------------------|----------------|----------------------|-----------------------|
| Transformers | ✅ | ✅\*\*\* | ✅\* | ✅ | ✅ | | Transformers | ✅ | ✅\*\* | ✅\* | ✅ | ✅ |
| llama.cpp | ❌ | ❌ | ❌ | ❌ | use llamacpp_HF | | llama.cpp | ❌ | ❌ | ❌ | ❌ | use llamacpp_HF |
| llamacpp_HF | ❌ | ❌ | ❌ | ❌ | ✅ | | llamacpp_HF | ❌ | ❌ | ❌ | ❌ | ✅ |
| ExLlamav2_HF | ✅ | ✅ | ❌ | ❌ | ✅ | | ExLlamav2_HF | ✅ | ✅ | ❌ | ❌ | ✅ |
| ExLlamav2 | ✅ | ✅ | ❌ | ❌ | use ExLlamav2_HF | | ExLlamav2 | ✅ | ✅ | ❌ | ❌ | use ExLlamav2_HF |
| AutoGPTQ | ✅ | ❌ | ❌ | ✅ | ✅ | | AutoGPTQ | ✅ | ❌ | ❌ | ✅ | ✅ |
| AutoAWQ | ? | ❌ | ? | ? | ✅ | | AutoAWQ | ? | ❌ | ? | ? | ✅ |
| GPTQ-for-LLaMa | ✅\*\* | ✅\*\*\* | ✅ | ✅ | ✅ |
| QuIP# | ? | ? | ? | ? | ✅ |
| HQQ | ? | ? | ? | ? | ✅ | | HQQ | ? | ? | ? | ? | ✅ |
❌ = not implemented ❌ = not implemented
@ -19,6 +17,4 @@
\* Training LoRAs with GPTQ models also works with the Transformers loader. Make sure to check "auto-devices" and "disable_exllama" before loading the model. \* Training LoRAs with GPTQ models also works with the Transformers loader. Make sure to check "auto-devices" and "disable_exllama" before loading the model.
\*\* Requires the monkey-patch. The instructions can be found [here](https://github.com/oobabooga/text-generation-webui/wiki/08-%E2%80%90-Additional-Tips#using-loras-with-gptq-for-llama). \*\* Multi-LoRA in PEFT is tricky and the current implementation does not work reliably in all cases.
\*\*\* Multi-LoRA in PEFT is tricky and the current implementation does not work reliably in all cases.

12
download-model.py
View File

@ -167,8 +167,11 @@ class ModelDownloader:
is_llamacpp = has_gguf and specific_file is not None is_llamacpp = has_gguf and specific_file is not None
return links, sha256, is_lora, is_llamacpp return links, sha256, is_lora, is_llamacpp
def get_output_folder(self, model, branch, is_lora, is_llamacpp=False): def get_output_folder(self, model, branch, is_lora, is_llamacpp=False, model_dir=None):
base_folder = 'models' if not is_lora else 'loras' if model_dir:
base_folder = model_dir
else:
base_folder = 'models' if not is_lora else 'loras'
# If the model is of type GGUF, save directly in the base_folder # If the model is of type GGUF, save directly in the base_folder
if is_llamacpp: if is_llamacpp:
@ -304,7 +307,8 @@ if __name__ == '__main__':
parser.add_argument('--threads', type=int, default=4, help='Number of files to download simultaneously.') parser.add_argument('--threads', type=int, default=4, help='Number of files to download simultaneously.')
parser.add_argument('--text-only', action='store_true', help='Only download text files (txt/json).') parser.add_argument('--text-only', action='store_true', help='Only download text files (txt/json).')
parser.add_argument('--specific-file', type=str, default=None, help='Name of the specific file to download (if not provided, downloads all).') parser.add_argument('--specific-file', type=str, default=None, help='Name of the specific file to download (if not provided, downloads all).')
parser.add_argument('--output', type=str, default=None, help='The folder where the model should be saved.') parser.add_argument('--output', type=str, default=None, help='Save the model files to this folder.')
parser.add_argument('--model-dir', type=str, default=None, help='Save the model files to a subfolder of this folder instead of the default one (text-generation-webui/models).')
parser.add_argument('--clean', action='store_true', help='Does not resume the previous download.') parser.add_argument('--clean', action='store_true', help='Does not resume the previous download.')
parser.add_argument('--check', action='store_true', help='Validates the checksums of model files.') parser.add_argument('--check', action='store_true', help='Validates the checksums of model files.')
parser.add_argument('--max-retries', type=int, default=5, help='Max retries count when get error in download time.') parser.add_argument('--max-retries', type=int, default=5, help='Max retries count when get error in download time.')
@ -333,7 +337,7 @@ if __name__ == '__main__':
if args.output: if args.output:
output_folder = Path(args.output) output_folder = Path(args.output)
else: else:
output_folder = downloader.get_output_folder(model, branch, is_lora, is_llamacpp=is_llamacpp) output_folder = downloader.get_output_folder(model, branch, is_lora, is_llamacpp=is_llamacpp, model_dir=args.model_dir)
if args.check: if args.check:
# Check previously downloaded files # Check previously downloaded files

4
extensions/openai/typing.py
View File

@ -34,6 +34,10 @@ class GenerationOptions(BaseModel):
seed: int = -1 seed: int = -1
encoder_repetition_penalty: float = 1 encoder_repetition_penalty: float = 1
no_repeat_ngram_size: int = 0 no_repeat_ngram_size: int = 0
dry_multiplier: float = 0
dry_base: float = 1.75
dry_allowed_length: int = 2
dry_sequence_breakers: str = '"\\n", ":", "\\"", "*"'
truncation_length: int = 0 truncation_length: int = 0
max_tokens_second: int = 0 max_tokens_second: int = 0
prompt_lookup_num_tokens: int = 0 prompt_lookup_num_tokens: int = 0

13
instruction-templates/Llama-v3.yaml Normal file
View File

@ -0,0 +1,13 @@
instruction_template: |-
{%- set ns = namespace(found=false) -%}
{%- for message in messages -%}
{%- if message['role'] == 'system' -%}
{%- set ns.found = true -%}
{%- endif -%}
{%- endfor -%}
{%- for message in messages -%}
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n' + message['content'].rstrip() + '<|eot_id|>' -}}
{%- endfor -%}
{%- if add_generation_prompt -%}
{{-'<|start_header_id|>assistant<|end_header_id|>\n\n'-}}
{%- endif -%}

2
modules/AutoGPTQ_loader.py
View File

@ -44,7 +44,7 @@ def load_quantized(model_name):
'model_basename': pt_path.stem, 'model_basename': pt_path.stem,
'device': "xpu:0" if is_xpu_available() else "cuda:0" if not shared.args.cpu else "cpu", 'device': "xpu:0" if is_xpu_available() else "cuda:0" if not shared.args.cpu else "cpu",
'use_triton': shared.args.triton, 'use_triton': shared.args.triton,
'inject_fused_attention': not shared.args.no_inject_fused_attention, 'inject_fused_attention': False,
'inject_fused_mlp': not shared.args.no_inject_fused_mlp, 'inject_fused_mlp': not shared.args.no_inject_fused_mlp,
'use_safetensors': use_safetensors, 'use_safetensors': use_safetensors,
'trust_remote_code': shared.args.trust_remote_code, 'trust_remote_code': shared.args.trust_remote_code,

171
modules/GPTQ_loader.py
View File

@ -1,171 +0,0 @@
import inspect
import re
from pathlib import Path
import accelerate
import torch
import transformers
from accelerate.utils import is_xpu_available
from gptq_for_llama import llama_inference_offload
from gptq_for_llama.modelutils import find_layers
from gptq_for_llama.quant import make_quant
from transformers import AutoConfig, AutoModelForCausalLM
import modules.shared as shared
from modules.logging_colors import logger
# This function is a replacement for the load_quant function in the
# GPTQ-for_LLaMa repository. It supports more models and branches.
def _load_quant(model, checkpoint, wbits, groupsize=-1, faster_kernel=False, exclude_layers=None, kernel_switch_threshold=128, eval=True):
exclude_layers = exclude_layers or ['lm_head']
def noop(*args, **kwargs):
pass
config = AutoConfig.from_pretrained(model, trust_remote_code=shared.args.trust_remote_code)
torch.nn.init.kaiming_uniform_ = noop
torch.nn.init.uniform_ = noop
torch.nn.init.normal_ = noop
torch.set_default_dtype(torch.half)
transformers.modeling_utils._init_weights = False
torch.set_default_dtype(torch.half)
model = AutoModelForCausalLM.from_config(config, trust_remote_code=shared.args.trust_remote_code)
torch.set_default_dtype(torch.float)
if eval:
model = model.eval()
layers = find_layers(model)
for name in exclude_layers:
if name in layers:
del layers[name]
gptq_args = inspect.getfullargspec(make_quant).args
make_quant_kwargs = {
'module': model,
'names': layers,
'bits': wbits,
}
if 'groupsize' in gptq_args:
make_quant_kwargs['groupsize'] = groupsize
if 'faster' in gptq_args:
make_quant_kwargs['faster'] = faster_kernel
if 'kernel_switch_threshold' in gptq_args:
make_quant_kwargs['kernel_switch_threshold'] = kernel_switch_threshold
make_quant(**make_quant_kwargs)
del layers
if checkpoint.endswith('.safetensors'):
from safetensors.torch import load_file as safe_load
model.load_state_dict(safe_load(checkpoint), strict=False)
else:
model.load_state_dict(torch.load(checkpoint, weights_only=True), strict=False)
model.seqlen = 2048
return model
# Used to locate the .pt/.safetensors quantized file
def find_quantized_model_file(model_name):
if shared.args.checkpoint:
return Path(shared.args.checkpoint)
path_to_model = Path(f'{shared.args.model_dir}/{model_name}')
pt_path = None
priority_name_list = [
Path(f'{shared.args.model_dir}/{model_name}{hyphen}{shared.args.wbits}bit{group}{ext}')
for group in ([f'-{shared.args.groupsize}g', ''] if shared.args.groupsize > 0 else [''])
for ext in ['.safetensors', '.pt']
for hyphen in ['-', f'/{model_name}-', '/']
]
for path in priority_name_list:
if path.exists():
pt_path = path
break
# If the model hasn't been found with a well-behaved name, pick the last .pt
# or the last .safetensors found in its folder as a last resort
if not pt_path:
for ext in ['.pt', '.safetensors']:
found = list(path_to_model.glob(f"*{ext}"))
if len(found) > 0:
if len(found) > 1:
logger.warning(f'More than one {ext} model has been found. The last one will be selected. It could be wrong.')
pt_path = found[-1]
break
return pt_path
# The function that loads the model in modules/models.py
def load_quantized(model_name):
if shared.args.model_type is None:
logger.error("The model could not be loaded because its type could not be inferred from its name.")
logger.error("Please specify the type manually using the --model_type argument.")
return None
# Select the appropriate load_quant function
model_type = shared.args.model_type.lower()
if shared.args.pre_layer and model_type == 'llama':
load_quant = llama_inference_offload.load_quant
elif model_type in ('llama', 'opt', 'gptj'):
if shared.args.pre_layer:
logger.warning("Ignoring --pre_layer because it only works for llama model type.")
load_quant = _load_quant
else:
logger.error("Unknown pre-quantized model type specified. Only 'llama', 'opt' and 'gptj' are supported")
exit()
# Find the quantized model weights file (.pt/.safetensors)
path_to_model = Path(f'{shared.args.model_dir}/{model_name}')
pt_path = find_quantized_model_file(model_name)
if not pt_path:
logger.error("Could not find the quantized model in .pt or .safetensors format. Exiting.")
exit()
else:
logger.info(f"Found the following quantized model: {pt_path}")
# qwopqwop200's offload
if model_type == 'llama' and shared.args.pre_layer:
if len(shared.args.pre_layer) == 1:
pre_layer = shared.args.pre_layer[0]
else:
pre_layer = shared.args.pre_layer
model = load_quant(str(path_to_model), str(pt_path), shared.args.wbits, shared.args.groupsize, pre_layer)
else:
threshold = False if model_type == 'gptj' else 128
model = load_quant(str(path_to_model), str(pt_path), shared.args.wbits, shared.args.groupsize, kernel_switch_threshold=threshold)
# accelerate offload (doesn't work properly)
if shared.args.gpu_memory or torch.cuda.device_count() > 1 or (is_xpu_available() and torch.xpu.device_count() > 1):
if shared.args.gpu_memory:
memory_map = list(map(lambda x: x.strip(), shared.args.gpu_memory))
max_cpu_memory = shared.args.cpu_memory.strip() if shared.args.cpu_memory is not None else '99GiB'
max_memory = {}
for i in range(len(memory_map)):
max_memory[i] = f'{memory_map[i]}GiB' if not re.match('.*ib$', memory_map[i].lower()) else memory_map[i]
max_memory['cpu'] = f'{max_cpu_memory}GiB' if not re.match('.*ib$', max_cpu_memory.lower()) else max_cpu_memory
else:
max_memory = accelerate.utils.get_balanced_memory(model)
device_map = accelerate.infer_auto_device_map(model, max_memory=max_memory, no_split_module_classes=["LlamaDecoderLayer"])
logger.info("Using the following device map for the quantized model:", device_map)
# https://huggingface.co/docs/accelerate/package_reference/big_modeling#accelerate.dispatch_model
model = accelerate.dispatch_model(model, device_map=device_map, offload_buffers=True)
# No offload
elif not shared.args.cpu:
if is_xpu_available():
model = model.to(torch.device("xpu:0"))
else:
model = model.to(torch.device('cuda:0'))
return model

8
modules/chat.py
View File

@ -308,9 +308,6 @@ def chatbot_wrapper(text, state, regenerate=False, _continue=False, loading_mess
'internal': output['internal'] 'internal': output['internal']
} }
if shared.model_name == 'None' or shared.model is None:
raise ValueError("No model is loaded! Select one in the Model tab.")
# Generate the prompt # Generate the prompt
kwargs = { kwargs = {
'_continue': _continue, '_continue': _continue,
@ -355,11 +352,6 @@ def impersonate_wrapper(text, state):
static_output = chat_html_wrapper(state['history'], state['name1'], state['name2'], state['mode'], state['chat_style'], state['character_menu']) static_output = chat_html_wrapper(state['history'], state['name1'], state['name2'], state['mode'], state['chat_style'], state['character_menu'])
if shared.model_name == 'None' or shared.model is None:
logger.error("No model is loaded! Select one in the Model tab.")
yield '', static_output
return
prompt = generate_chat_prompt('', state, impersonate=True) prompt = generate_chat_prompt('', state, impersonate=True)
stopping_strings = get_stopping_strings(state) stopping_strings = get_stopping_strings(state)

53
modules/grammar/grammar_utils.py
View File

@ -60,7 +60,7 @@ def hex_to_int(c):
return int(c) return int(c)
elif "a" <= c.lower() <= "f": elif "a" <= c.lower() <= "f":
return ord(c.lower()) - ord("a") + 10 return ord(c.lower()) - ord("a") + 10
return -1 raise RuntimeError("unknown hex char " + c)
def remove_leading_white_space(src, newline_ok): def remove_leading_white_space(src, newline_ok):
@ -100,6 +100,13 @@ def parse_name(src):
return src[:pos], src[pos:] return src[:pos], src[pos:]
def read_hex(s):
val = 0
for c in s:
val = (val << 4) + hex_to_int(c)
return chr(val)
def parse_char(src): def parse_char(src):
""" """
parse the leading char from the input string parse the leading char from the input string
@ -111,13 +118,12 @@ def parse_char(src):
if src[0] == "\\": if src[0] == "\\":
esc = src[1] esc = src[1]
if esc == "x": if esc == "x":
first = hex_to_int(src[2]) return read_hex(src[2:4]), src[4:]
if first > -1: elif esc == "u":
second = hex_to_int(src[3]) return read_hex(src[2:6]), src[6:]
if second > -1: elif esc == "U":
return (first << 4) + second, src[4:] return read_hex(src[2:10]), src[10:]
raise RuntimeError("expecting \\xNN at " + src) elif esc in ('"', "[", "]", "\\", "-"):
elif esc in ('"', "[", "]"):
return esc, src[2:] return esc, src[2:]
elif esc == "r": elif esc == "r":
return "\r", src[2:] return "\r", src[2:]
@ -125,6 +131,8 @@ def parse_char(src):
return "\n", src[2:] return "\n", src[2:]
elif esc == "t": elif esc == "t":
return "\t", src[2:] return "\t", src[2:]
elif esc == "\\":
return "\\", src[2:]
raise RuntimeError("unknown escape at " + src) raise RuntimeError("unknown escape at " + src)
elif src: elif src:
return src[0], src[1:] return src[0], src[1:]
@ -454,7 +462,8 @@ class IncrementalGrammarConstraint(GrammarConstraint):
def __init__(self, grammar_str, start_rule_name, tokenizer): def __init__(self, grammar_str, start_rule_name, tokenizer):
super().__init__(grammar_str, start_rule_name, tokenizer) super().__init__(grammar_str, start_rule_name, tokenizer)
def accept_char(self, byte, stacks): def accept_char(self, char, stacks):
byte = ord(char)
new_stacks = [] new_stacks = []
for stack in stacks: for stack in stacks:
# stack is empty # stack is empty
@ -471,6 +480,9 @@ class IncrementalGrammarConstraint(GrammarConstraint):
if self.grammar_encoding[pos + i] <= byte and byte <= self.grammar_encoding[pos + i + 1]: if self.grammar_encoding[pos + i] <= byte and byte <= self.grammar_encoding[pos + i + 1]:
found = True found = True
break break
if self.grammar_encoding[pos + i] >= byte and byte >= self.grammar_encoding[pos + i + 1]:
found = True
break
if not found: if not found:
continue continue
@ -483,9 +495,8 @@ class IncrementalGrammarConstraint(GrammarConstraint):
return new_stacks return new_stacks
def accept_string(self, string: str, stacks: List[List[int]]): def accept_string(self, string: str, stacks: List[List[int]]):
_bytes = bytes(string, "utf-8") for char in string:
for byte in _bytes: stacks = self.accept_char(char, stacks)
stacks = self.accept_char(byte, stacks)
return stacks return stacks
def accept_token_id(self, token_id: int, stacks: List[List[int]]): def accept_token_id(self, token_id: int, stacks: List[List[int]]):
@ -537,16 +548,18 @@ class IncrementalGrammarConstraint(GrammarConstraint):
# For each sub-rule in the grammar, cache whether each byte is accepted. # For each sub-rule in the grammar, cache whether each byte is accepted.
@lru_cache(maxsize=None) @lru_cache(maxsize=None)
def pos_char_acceptance(self, pos): def pos_char_acceptance(self, pos, char):
acceptance = [False] * 256 byte = ord(char)
num_chars = self.grammar_encoding[pos] num_chars = self.grammar_encoding[pos]
pos += 1 pos += 1
for i in range(0, num_chars, 2): for i in range(0, num_chars, 2):
start = self.grammar_encoding[pos + i] start = self.grammar_encoding[pos + i]
end = self.grammar_encoding[pos + i + 1] end = self.grammar_encoding[pos + i + 1]
for j in range(start, end + 1): if byte >= start and byte <= end:
acceptance[j] = True return True
return acceptance if byte <= start and byte >= end:
return True
return False
# Probably this should be configurable. If the grammar has an exceedingly # Probably this should be configurable. If the grammar has an exceedingly
# large number of states, the correct setting is a tradeoff between GPU # large number of states, the correct setting is a tradeoff between GPU
@ -580,7 +593,7 @@ class IncrementalGrammarConstraint(GrammarConstraint):
pos = stk[-1] pos = stk[-1]
num_chars = self.grammar_encoding[pos] num_chars = self.grammar_encoding[pos]
if not self.pos_char_acceptance(pos)[byte]: if not self.pos_char_acceptance(pos, byte):
continue continue
pos += num_chars + 1 pos += num_chars + 1
@ -657,14 +670,14 @@ class TokenTrie:
token = tokenizer.convert_ids_to_tokens(id) token = tokenizer.convert_ids_to_tokens(id)
token = re.sub(r"<0x([0-9a-fA-F]{2})>", replace_hex, token) token = re.sub(r"<0x([0-9a-fA-F]{2})>", replace_hex, token)
token = token.replace("▁", " ") token = token.replace("▁", " ")
return bytes(token, "utf-8") return token
else: else:
print("Warning: unrecognized tokenizer: using default token formatting") print("Warning: unrecognized tokenizer: using default token formatting")
def fmt_token(id): def fmt_token(id):
token = tokenizer.convert_ids_to_tokens(id) token = tokenizer.convert_ids_to_tokens(id)
return bytes(token, "utf-8") return token
# note: vocab_size doesn't work here because there are also # note: vocab_size doesn't work here because there are also
# get_added_vocab() tokens # get_added_vocab() tokens

46
modules/loaders.py
View File

@ -105,7 +105,6 @@ loaders_and_params = OrderedDict({
], ],
'AutoGPTQ': [ 'AutoGPTQ': [
'triton', 'triton',
'no_inject_fused_attention',
'no_inject_fused_mlp', 'no_inject_fused_mlp',
'no_use_cuda_fp16', 'no_use_cuda_fp16',
'wbits', 'wbits',
@ -131,21 +130,6 @@ loaders_and_params = OrderedDict({
'trust_remote_code', 'trust_remote_code',
'no_use_fast', 'no_use_fast',
], ],
'GPTQ-for-LLaMa': [
'wbits',
'groupsize',
'model_type',
'pre_layer',
'trust_remote_code',
'no_use_fast',
'gptq_for_llama_info',
],
'QuIP#': [
'trust_remote_code',
'no_use_fast',
'no_flash_attn',
'quipsharp_info',
],
'HQQ': [ 'HQQ': [
'hqq_backend', 'hqq_backend',
'trust_remote_code', 'trust_remote_code',
@ -178,6 +162,10 @@ def transformers_samplers():
'repetition_penalty_range', 'repetition_penalty_range',
'encoder_repetition_penalty', 'encoder_repetition_penalty',
'no_repeat_ngram_size', 'no_repeat_ngram_size',
'dry_multiplier',
'dry_base',
'dry_allowed_length',
'dry_sequence_breakers',
'seed', 'seed',
'do_sample', 'do_sample',
'penalty_alpha', 'penalty_alpha',
@ -201,9 +189,7 @@ def transformers_samplers():
loaders_samplers = { loaders_samplers = {
'Transformers': transformers_samplers(), 'Transformers': transformers_samplers(),
'AutoGPTQ': transformers_samplers(), 'AutoGPTQ': transformers_samplers(),
'GPTQ-for-LLaMa': transformers_samplers(),
'AutoAWQ': transformers_samplers(), 'AutoAWQ': transformers_samplers(),
'QuIP#': transformers_samplers(),
'HQQ': transformers_samplers(), 'HQQ': transformers_samplers(),
'ExLlamav2': { 'ExLlamav2': {
'temperature', 'temperature',
@ -251,6 +237,10 @@ loaders_samplers = {
'repetition_penalty_range', 'repetition_penalty_range',
'encoder_repetition_penalty', 'encoder_repetition_penalty',
'no_repeat_ngram_size', 'no_repeat_ngram_size',
'dry_multiplier',
'dry_base',
'dry_allowed_length',
'dry_sequence_breakers',
'seed', 'seed',
'do_sample', 'do_sample',
'mirostat_mode', 'mirostat_mode',
@ -309,6 +299,10 @@ loaders_samplers = {
'repetition_penalty_range', 'repetition_penalty_range',
'encoder_repetition_penalty', 'encoder_repetition_penalty',
'no_repeat_ngram_size', 'no_repeat_ngram_size',
'dry_multiplier',
'dry_base',
'dry_allowed_length',
'dry_sequence_breakers',
'seed', 'seed',
'do_sample', 'do_sample',
'mirostat_mode', 'mirostat_mode',
@ -327,15 +321,6 @@ loaders_samplers = {
}, },
} }
loaders_model_types = {
'GPTQ-for-LLaMa': [
"None",
"llama",
"opt",
"gptj"
],
}
@functools.cache @functools.cache
def list_all_samplers(): def list_all_samplers():
@ -363,13 +348,6 @@ def blacklist_samplers(loader, dynamic_temperature):
return output return output
def get_model_types(loader):
if loader in loaders_model_types:
return loaders_model_types[loader]
return ["None"]
def get_gpu_memory_keys(): def get_gpu_memory_keys():
return [k for k in shared.gradio if k.startswith('gpu_memory')] return [k for k in shared.gradio if k.startswith('gpu_memory')]

33
modules/logits.py
View File

@ -1,14 +1,34 @@
import time
import traceback
import torch import torch
from transformers import is_torch_npu_available, is_torch_xpu_available from transformers import is_torch_npu_available, is_torch_xpu_available
from modules import sampler_hijack, shared from modules import models, sampler_hijack, shared
from modules.logging_colors import logger from modules.logging_colors import logger
from modules.models import load_model
from modules.text_generation import generate_reply from modules.text_generation import generate_reply
global_scores = None global_scores = None
def get_next_logits(prompt, state, use_samplers, previous, top_logits=25, return_dict=False): def get_next_logits(*args, **kwargs):
if shared.args.idle_timeout > 0 and shared.model is None and shared.previous_model_name not in [None, 'None']:
shared.model, shared.tokenizer = load_model(shared.previous_model_name)
shared.generation_lock.acquire()
try:
result = _get_next_logits(*args, **kwargs)
except Exception:
traceback.print_exc()
result = None
models.last_generation_time = time.time()
shared.generation_lock.release()
return result
def _get_next_logits(prompt, state, use_samplers, previous, top_logits=25, return_dict=False):
if shared.model is None: if shared.model is None:
logger.error("No model is loaded! Select one in the Model tab.") logger.error("No model is loaded! Select one in the Model tab.")
return 'Error: No model is loaded1 Select one in the Model tab.', previous return 'Error: No model is loaded1 Select one in the Model tab.', previous
@ -66,7 +86,14 @@ def get_next_logits(prompt, state, use_samplers, previous, top_logits=25, return
topk_values = [float(i) for i in topk_values] topk_values = [float(i) for i in topk_values]
output = {} output = {}
for row in list(zip(topk_values, tokens)): for row in list(zip(topk_values, tokens)):
output[row[1]] = row[0] key = row[1]
if isinstance(key, bytes):
try:
key = key.decode()
except:
key = key.decode('latin')
output[key] = row[0]
return output return output
else: else:

79
modules/models.py
View File

@ -61,6 +61,9 @@ if shared.args.deepspeed:
sampler_hijack.hijack_samplers() sampler_hijack.hijack_samplers()
last_generation_time = time.time()
def load_model(model_name, loader=None): def load_model(model_name, loader=None):
logger.info(f"Loading \"{model_name}\"") logger.info(f"Loading \"{model_name}\"")
t0 = time.time() t0 = time.time()
@ -70,13 +73,11 @@ def load_model(model_name, loader=None):
load_func_map = { load_func_map = {
'Transformers': huggingface_loader, 'Transformers': huggingface_loader,
'AutoGPTQ': AutoGPTQ_loader, 'AutoGPTQ': AutoGPTQ_loader,
'GPTQ-for-LLaMa': GPTQ_loader,
'llama.cpp': llamacpp_loader, 'llama.cpp': llamacpp_loader,
'llamacpp_HF': llamacpp_HF_loader, 'llamacpp_HF': llamacpp_HF_loader,
'ExLlamav2': ExLlamav2_loader, 'ExLlamav2': ExLlamav2_loader,
'ExLlamav2_HF': ExLlamav2_HF_loader, 'ExLlamav2_HF': ExLlamav2_HF_loader,
'AutoAWQ': AutoAWQ_loader, 'AutoAWQ': AutoAWQ_loader,
'QuIP#': QuipSharp_loader,
'HQQ': HQQ_loader, 'HQQ': HQQ_loader,
} }
@ -266,7 +267,7 @@ def llamacpp_loader(model_name):
if path.is_file(): if path.is_file():
model_file = path model_file = path
else: else:
model_file = list(Path(f'{shared.args.model_dir}/{model_name}').glob('*.gguf'))[0] model_file = sorted(Path(f'{shared.args.model_dir}/{model_name}').glob('*.gguf'))[0]
logger.info(f"llama.cpp weights detected: \"{model_file}\"") logger.info(f"llama.cpp weights detected: \"{model_file}\"")
model, tokenizer = LlamaCppModel.from_pretrained(model_file) model, tokenizer = LlamaCppModel.from_pretrained(model_file)
@ -307,55 +308,6 @@ def AutoAWQ_loader(model_name):
return model return model
def QuipSharp_loader(model_name):
try:
with RelativeImport("repositories/quip-sharp"):
from lib.utils.unsafe_import import model_from_hf_path
except:
logger.error(
"\nQuIP# has not been found. It must be installed manually for now.\n"
"For instructions on how to do that, please consult:\n"
"https://github.com/oobabooga/text-generation-webui/pull/4803\n"
)
return None, None
# This fixes duplicate logging messages after the import above.
handlers = logging.getLogger().handlers
if len(handlers) > 1:
logging.getLogger().removeHandler(handlers[1])
model_dir = Path(f'{shared.args.model_dir}/{model_name}')
if not all((model_dir / file).exists() for file in ['tokenizer_config.json', 'special_tokens_map.json', 'tokenizer.model']):
logger.error(f"Could not load the model because the tokenizer files could not be found in the model folder. Please download the following files from the original (unquantized) model into {model_dir}: special_tokens_map.json, tokenizer.json, tokenizer.model, tokenizer_config.json.")
return None, None
model, model_str = model_from_hf_path(
model_dir,
use_cuda_graph=False,
use_flash_attn=not shared.args.no_flash_attn
)
return model
def GPTQ_loader(model_name):
# Monkey patch
if shared.args.monkey_patch:
logger.warning("Applying the monkey patch for using LoRAs with GPTQ models. It may cause undefined behavior outside its intended scope.")
from modules.monkey_patch_gptq_lora import load_model_llama
model, _ = load_model_llama(model_name)
# No monkey patch
else:
import modules.GPTQ_loader
model = modules.GPTQ_loader.load_quantized(model_name)
return model
def AutoGPTQ_loader(model_name): def AutoGPTQ_loader(model_name):
import modules.AutoGPTQ_loader import modules.AutoGPTQ_loader
@ -377,12 +329,12 @@ def ExLlamav2_HF_loader(model_name):
def HQQ_loader(model_name): def HQQ_loader(model_name):
from hqq.core.quantize import HQQBackend, HQQLinear from hqq.core.quantize import HQQBackend, HQQLinear
from hqq.engine.hf import HQQModelForCausalLM from hqq.models.hf.base import AutoHQQHFModel
logger.info(f"Loading HQQ model with backend: \"{shared.args.hqq_backend}\"") logger.info(f"Loading HQQ model with backend: \"{shared.args.hqq_backend}\"")
model_dir = Path(f'{shared.args.model_dir}/{model_name}') model_dir = Path(f'{shared.args.model_dir}/{model_name}')
model = HQQModelForCausalLM.from_quantized(str(model_dir)) model = AutoHQQHFModel.from_quantized(str(model_dir))
HQQLinear.set_backend(getattr(HQQBackend, shared.args.hqq_backend)) HQQLinear.set_backend(getattr(HQQBackend, shared.args.hqq_backend))
return model return model
@ -428,6 +380,7 @@ def clear_torch_cache():
def unload_model(): def unload_model():
shared.model = shared.tokenizer = None shared.model = shared.tokenizer = None
shared.previous_model_name = shared.model_name
shared.model_name = 'None' shared.model_name = 'None'
shared.lora_names = [] shared.lora_names = []
shared.model_dirty_from_training = False shared.model_dirty_from_training = False
@ -437,3 +390,21 @@ def unload_model():
def reload_model(): def reload_model():
unload_model() unload_model()
shared.model, shared.tokenizer = load_model(shared.model_name) shared.model, shared.tokenizer = load_model(shared.model_name)
def unload_model_if_idle():
global last_generation_time
logger.info(f"Setting a timeout of {shared.args.idle_timeout} minutes to unload the model in case of inactivity.")
while True:
shared.generation_lock.acquire()
try:
if time.time() - last_generation_time > shared.args.idle_timeout * 60:
if shared.model is not None:
logger.info("Unloading the model for inactivity.")
unload_model()
finally:
shared.generation_lock.release()
time.sleep(60)

16
modules/models_settings.py
View File

@ -12,7 +12,6 @@ def get_fallback_settings():
'wbits': 'None', 'wbits': 'None',
'groupsize': 'None', 'groupsize': 'None',
'desc_act': False, 'desc_act': False,
'model_type': 'None',
'max_seq_len': 2048, 'max_seq_len': 2048,
'n_ctx': 2048, 'n_ctx': 2048,
'rope_freq_base': 0, 'rope_freq_base': 0,
@ -40,12 +39,7 @@ def get_model_metadata(model):
hf_metadata = None hf_metadata = None
if 'loader' not in model_settings: if 'loader' not in model_settings:
if hf_metadata is not None and 'quip_params' in hf_metadata: model_settings['loader'] = infer_loader(model, model_settings)
loader = 'QuIP#'
else:
loader = infer_loader(model, model_settings)
model_settings['loader'] = loader
# GGUF metadata # GGUF metadata
if model_settings['loader'] in ['llama.cpp', 'llamacpp_HF']: if model_settings['loader'] in ['llama.cpp', 'llamacpp_HF']:
@ -56,6 +50,7 @@ def get_model_metadata(model):
model_file = list(path.glob('*.gguf'))[0] model_file = list(path.glob('*.gguf'))[0]
metadata = metadata_gguf.load_metadata(model_file) metadata = metadata_gguf.load_metadata(model_file)
for k in metadata: for k in metadata:
if k.endswith('context_length'): if k.endswith('context_length'):
model_settings['n_ctx'] = metadata[k] model_settings['n_ctx'] = metadata[k]
@ -63,6 +58,9 @@ def get_model_metadata(model):
model_settings['rope_freq_base'] = metadata[k] model_settings['rope_freq_base'] = metadata[k]
elif k.endswith('rope.scale_linear'): elif k.endswith('rope.scale_linear'):
model_settings['compress_pos_emb'] = metadata[k] model_settings['compress_pos_emb'] = metadata[k]
elif k.endswith('block_count'):
model_settings['n_gpu_layers'] = metadata[k] + 1
if 'tokenizer.chat_template' in metadata: if 'tokenizer.chat_template' in metadata:
template = metadata['tokenizer.chat_template'] template = metadata['tokenizer.chat_template']
eos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.eos_token_id']] eos_token = metadata['tokenizer.ggml.tokens'][metadata['tokenizer.ggml.eos_token_id']]
@ -200,7 +198,7 @@ def update_model_parameters(state, initial=False):
continue continue
# Setting null defaults # Setting null defaults
if element in ['wbits', 'groupsize', 'model_type'] and value == 'None': if element in ['wbits', 'groupsize'] and value == 'None':
value = vars(shared.args_defaults)[element] value = vars(shared.args_defaults)[element]
elif element in ['cpu_memory'] and value == 0: elif element in ['cpu_memory'] and value == 0:
value = vars(shared.args_defaults)[element] value = vars(shared.args_defaults)[element]
@ -238,7 +236,7 @@ def apply_model_settings_to_state(model, state):
loader = model_settings.pop('loader') loader = model_settings.pop('loader')
# If the user is using an alternative loader for the same model type, let them keep using it # If the user is using an alternative loader for the same model type, let them keep using it
if not (loader == 'ExLlamav2_HF' and state['loader'] in ['GPTQ-for-LLaMa', 'ExLlamav2', 'AutoGPTQ']): if not (loader == 'ExLlamav2_HF' and state['loader'] in ['ExLlamav2', 'AutoGPTQ']):
state['loader'] = loader state['loader'] = loader
for k in model_settings: for k in model_settings:

39
modules/monkey_patch_gptq_lora.py
View File

@ -1,39 +0,0 @@
# Copied from https://github.com/johnsmith0031/alpaca_lora_4bit
from pathlib import Path
import alpaca_lora_4bit.autograd_4bit as autograd_4bit
from alpaca_lora_4bit.amp_wrapper import AMPWrapper
from alpaca_lora_4bit.autograd_4bit import (
Autograd4bitQuantLinear,
load_llama_model_4bit_low_ram
)
from alpaca_lora_4bit.models import Linear4bitLt
from alpaca_lora_4bit.monkeypatch.peft_tuners_lora_monkey_patch import (
replace_peft_model_with_int4_lora_model
)
from modules import shared
from modules.GPTQ_loader import find_quantized_model_file
replace_peft_model_with_int4_lora_model()
def load_model_llama(model_name):
config_path = str(Path(f'{shared.args.model_dir}/{model_name}'))
model_path = str(find_quantized_model_file(model_name))
model, tokenizer = load_llama_model_4bit_low_ram(config_path, model_path, groupsize=shared.args.groupsize, is_v1_model=False)
for _, m in model.named_modules():
if isinstance(m, Autograd4bitQuantLinear) or isinstance(m, Linear4bitLt):
if m.is_v1_model:
m.zeros = m.zeros.half()
m.scales = m.scales.half()
m.bias = m.bias.half()
autograd_4bit.auto_switch = True
model.half()
wrapper = AMPWrapper(model)
wrapper.apply_generate()
return model, tokenizer

4
modules/presets.py
View File

@ -40,6 +40,10 @@ def default_preset():
'do_sample': True, 'do_sample': True,
'encoder_repetition_penalty': 1, 'encoder_repetition_penalty': 1,
'no_repeat_ngram_size': 0, 'no_repeat_ngram_size': 0,
'dry_multiplier': 0,
'dry_base': 1.75,
'dry_allowed_length': 2,
'dry_sequence_breakers': '"\\n", ":", "\\"", "*"',
'sampler_priority': 'temperature\ndynamic_temperature\nquadratic_sampling\ntop_k\ntop_p\ntypical_p\nepsilon_cutoff\neta_cutoff\ntfs\ntop_a\nmin_p\nmirostat' 'sampler_priority': 'temperature\ndynamic_temperature\nquadratic_sampling\ntop_k\ntop_p\ntypical_p\nepsilon_cutoff\neta_cutoff\ntfs\ntop_a\nmin_p\nmirostat'
} }

149
modules/sampler_hijack.py
View File

@ -1,3 +1,4 @@
import json
import math import math
import pprint import pprint
@ -124,36 +125,6 @@ class QuadraticSamplingLogitsWarper(LogitsWarper):
return transformed_logits return transformed_logits
class MinPLogitsWarper(LogitsWarper):
def __init__(self, min_p: float, filter_value: float = -float("Inf"), min_tokens_to_keep: int = 1):
if min_p < 0 or min_p > 1.0:
raise ValueError(f"`min_p` has to be a float >= 0 and <= 1, but is {min_p}")
self.min_p = min_p
self.filter_value = filter_value
self.min_tokens_to_keep = min_tokens_to_keep
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
# Convert logits to probabilities
probs = torch.softmax(scores, dim=-1)
# Get the probability of the top token for each sequence in the batch
top_probs, _ = probs.max(dim=-1, keepdim=True)
# Calculate the actual min_p threshold by scaling min_p with the top token's probability
scaled_min_p = self.min_p * top_probs
# Create a mask for tokens that have a probability less than the scaled min_p
tokens_to_remove = probs < scaled_min_p
sorted_indices = torch.argsort(scores, descending=True, dim=-1)
sorted_indices_to_remove = torch.gather(tokens_to_remove, dim=-1, index=sorted_indices)
if self.min_tokens_to_keep > 1:
# Keep at least min_tokens_to_keep
sorted_indices_to_remove[..., : self.min_tokens_to_keep] = False
indices_to_remove = sorted_indices_to_remove.scatter(1, sorted_indices, sorted_indices_to_remove)
scores = scores.masked_fill(indices_to_remove, self.filter_value)
return scores
class TailFreeLogitsWarper(LogitsWarper): class TailFreeLogitsWarper(LogitsWarper):
def __init__(self, tfs: float, filter_value: float = -float("Inf"), min_tokens_to_keep: int = 1): def __init__(self, tfs: float, filter_value: float = -float("Inf"), min_tokens_to_keep: int = 1):
tfs = float(tfs) tfs = float(tfs)
@ -220,6 +191,74 @@ class TopALogitsWarper(LogitsWarper):
return scores return scores
class DRYLogitsProcessor(LogitsProcessor):
def __init__(self, multiplier: float, base: float, allowed_length: int, sequence_breakers: set[int], _range: int):
self.multiplier = multiplier
self.base = base
self.allowed_length = allowed_length
self.sequence_breakers = sequence_breakers
self._range = _range
def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:
if self._range > 0:
input_ids = input_ids[:, -self._range:]
for input_ids_row, scores_row in zip(input_ids, scores):
# Raw integer must be extracted here to check for set membership.
last_token = input_ids_row[-1].item()
if last_token in self.sequence_breakers:
continue
# Exclude the last token as it always matches.
match_indices = (input_ids_row[:-1] == last_token).nonzero()
# Stores the maximum matching sequence length
# for each token immediately following the sequence in the input.
match_lengths = {}
for i in match_indices:
next_token = input_ids_row[i+1].item()
if next_token in self.sequence_breakers:
continue
# We have already found that `last_token` matches at this index,
# so the match is at least of length 1.
match_length = 1
# Extend the match backwards as far as possible.
while True:
j = i - match_length
if j < 0:
# Start of input reached.
break
previous_token = input_ids_row[-(match_length+1)].item()
if input_ids_row[j] != previous_token:
# Start of match reached.
break
if previous_token in self.sequence_breakers:
# Sequence-breaking token reached.
break
match_length += 1
if next_token in match_lengths:
match_lengths[next_token] = max(match_length, match_lengths[next_token])
else:
match_lengths[next_token] = match_length
# Apply penalties.
for token, match_length in match_lengths.items():
if match_length >= self.allowed_length:
penalty = self.multiplier * self.base ** (match_length - self.allowed_length)
scores_row[token] -= penalty
return scores
class MirostatLogitsWarper(LogitsWarper): class MirostatLogitsWarper(LogitsWarper):
def __init__(self, mirostat_mode: int, mirostat_tau: float, mirostat_eta: float, filter_value: float = -float("Inf"), min_tokens_to_keep: int = 1): def __init__(self, mirostat_mode: int, mirostat_tau: float, mirostat_eta: float, filter_value: float = -float("Inf"), min_tokens_to_keep: int = 1):
if mirostat_mode not in [2]: if mirostat_mode not in [2]:
@ -352,14 +391,6 @@ def get_logits_warper_patch(self, generation_config):
) )
) )
if generation_config.min_p is not None and 0.0 < generation_config.min_p <= 1.0:
warpers_to_add.append(
MinPLogitsWarper(
min_p=generation_config.min_p,
min_tokens_to_keep=min_tokens_to_keep
)
)
if generation_config.dynamic_temperature: if generation_config.dynamic_temperature:
warpers_to_add.append( warpers_to_add.append(
DynamicTemperatureLogitsWarper( DynamicTemperatureLogitsWarper(
@ -448,20 +479,44 @@ def get_logits_warper_patch(self, generation_config):
def get_logits_processor_patch(self, **kwargs): def get_logits_processor_patch(self, **kwargs):
repetition_penalty = kwargs['generation_config'].repetition_penalty generation_config = kwargs['generation_config']
presence_penalty = kwargs['generation_config'].presence_penalty
frequency_penalty = kwargs['generation_config'].frequency_penalty do_rep_pen_hijack = (generation_config.repetition_penalty > 1) or (generation_config.presence_penalty != 0) or (generation_config.frequency_penalty != 0)
repetition_penalty_range = kwargs['generation_config'].repetition_penalty_range
do_rep_pen_hijack = (repetition_penalty > 1) or (presence_penalty != 0) or (frequency_penalty != 0)
if do_rep_pen_hijack: if do_rep_pen_hijack:
kwargs['generation_config'].repetition_penalty = 1.1 # Set to value > 1 to ensure RepetitionPenaltyLogitsProcessor is created generation_config.repetition_penalty = 1.1 # Set to value > 1 to ensure RepetitionPenaltyLogitsProcessor is created
result = self._get_logits_processor_old(**kwargs) result = self._get_logits_processor_old(**kwargs)
if do_rep_pen_hijack: if do_rep_pen_hijack:
for i in range(len(result)): for i in range(len(result)):
if result[i].__class__.__name__ == 'RepetitionPenaltyLogitsProcessor': if result[i].__class__.__name__ == 'RepetitionPenaltyLogitsProcessor':
result[i] = RepetitionPenaltyLogitsProcessorWithRange(repetition_penalty, presence_penalty, frequency_penalty, repetition_penalty_range) result[i] = RepetitionPenaltyLogitsProcessorWithRange(
generation_config.repetition_penalty,
generation_config.presence_penalty,
generation_config.frequency_penalty,
generation_config.repetition_penalty_range
)
if generation_config.dry_multiplier is not None and generation_config.dry_multiplier > 0.0:
dry_sequence_breakers = generation_config.dry_sequence_breakers
# Support both JSON array notation and comma-separated strings.
if not dry_sequence_breakers.startswith("["):
dry_sequence_breakers = "[" + dry_sequence_breakers + "]"
sequence_breaker_strings = json.loads(dry_sequence_breakers)
# Prefix with 'a' to get the correct encoding of the token at the end of a text.
sequence_breakers = {shared.tokenizer.encode(f'a{s}')[-1] for s in sequence_breaker_strings}
result.append(
DRYLogitsProcessor(
multiplier=generation_config.dry_multiplier,
base=generation_config.dry_base,
allowed_length=generation_config.dry_allowed_length,
sequence_breakers=sequence_breakers,
_range=generation_config.repetition_penalty_range,
)
)
return result return result
@ -483,6 +538,10 @@ def generation_config_init_patch(self, **kwargs):
self.repetition_penalty_range = kwargs.pop("repetition_penalty_range", 0) self.repetition_penalty_range = kwargs.pop("repetition_penalty_range", 0)
self.presence_penalty = kwargs.pop("presence_penalty", 0) self.presence_penalty = kwargs.pop("presence_penalty", 0)
self.frequency_penalty = kwargs.pop("frequency_penalty", 0) self.frequency_penalty = kwargs.pop("frequency_penalty", 0)
self.dry_multiplier = kwargs.pop("dry_multiplier", 0.0)
self.dry_base = kwargs.pop("dry_base", 1.75)
self.dry_allowed_length = kwargs.pop("dry_allowed_length", 2)
self.dry_sequence_breakers = kwargs.pop("dry_sequence_breakers", '"\\n", ":", "\\"", "*"')
self.temperature_last = kwargs.pop("temperature_last", False) self.temperature_last = kwargs.pop("temperature_last", False)
self.sampler_priority = kwargs.pop("sampler_priority", ['temperature', 'dynamic_temperature', 'quadratic_sampling', 'top_k', 'top_p', 'typical_p', 'epsilon_cutoff', 'eta_cutoff', 'tfs', 'top_a', 'min_p', 'mirostat']) self.sampler_priority = kwargs.pop("sampler_priority", ['temperature', 'dynamic_temperature', 'quadratic_sampling', 'top_k', 'top_p', 'typical_p', 'epsilon_cutoff', 'eta_cutoff', 'tfs', 'top_a', 'min_p', 'mirostat'])

26
modules/shared.py
View File

@ -13,6 +13,7 @@ from modules.logging_colors import logger
model = None model = None
tokenizer = None tokenizer = None
model_name = 'None' model_name = 'None'
previous_model_name = 'None'
is_seq2seq = False is_seq2seq = False
model_dirty_from_training = False model_dirty_from_training = False
lora_names = [] lora_names = []
@ -84,10 +85,11 @@ group.add_argument('--settings', type=str, help='Load the default interface sett
group.add_argument('--extensions', type=str, nargs='+', help='The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.') group.add_argument('--extensions', type=str, nargs='+', help='The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.')
group.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.') group.add_argument('--verbose', action='store_true', help='Print the prompts to the terminal.')
group.add_argument('--chat-buttons', action='store_true', help='Show buttons on the chat tab instead of a hover menu.') group.add_argument('--chat-buttons', action='store_true', help='Show buttons on the chat tab instead of a hover menu.')
group.add_argument('--idle-timeout', type=int, default=0, help='Unload model after this many minutes of inactivity. It will be automatically reloaded when you try to use it again.')
# Model loader # Model loader
group = parser.add_argument_group('Model loader') group = parser.add_argument_group('Model loader')
group.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlamav2_HF, ExLlamav2, AutoGPTQ, AutoAWQ, GPTQ-for-LLaMa, QuIP#.') group.add_argument('--loader', type=str, help='Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, llamacpp_HF, ExLlamav2_HF, ExLlamav2, AutoGPTQ, AutoAWQ.')
# Transformers/Accelerate # Transformers/Accelerate
group = parser.add_argument_group('Transformers/Accelerate') group = parser.add_argument_group('Transformers/Accelerate')
@ -147,21 +149,17 @@ group.add_argument('--num_experts_per_token', type=int, default=2, help='Number
# AutoGPTQ # AutoGPTQ
group = parser.add_argument_group('AutoGPTQ') group = parser.add_argument_group('AutoGPTQ')
group.add_argument('--triton', action='store_true', help='Use triton.') group.add_argument('--triton', action='store_true', help='Use triton.')
group.add_argument('--no_inject_fused_attention', action='store_true', help='Disable the use of fused attention, which will use less VRAM at the cost of slower inference.')
group.add_argument('--no_inject_fused_mlp', action='store_true', help='Triton mode only: disable the use of fused MLP, which will use less VRAM at the cost of slower inference.') group.add_argument('--no_inject_fused_mlp', action='store_true', help='Triton mode only: disable the use of fused MLP, which will use less VRAM at the cost of slower inference.')
group.add_argument('--no_use_cuda_fp16', action='store_true', help='This can make models faster on some systems.') group.add_argument('--no_use_cuda_fp16', action='store_true', help='This can make models faster on some systems.')
group.add_argument('--desc_act', action='store_true', help='For models that do not have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig.') group.add_argument('--desc_act', action='store_true', help='For models that do not have a quantize_config.json, this parameter is used to define whether to set desc_act or not in BaseQuantizeConfig.')
group.add_argument('--disable_exllama', action='store_true', help='Disable ExLlama kernel, which can improve inference speed on some systems.') group.add_argument('--disable_exllama', action='store_true', help='Disable ExLlama kernel, which can improve inference speed on some systems.')
group.add_argument('--disable_exllamav2', action='store_true', help='Disable ExLlamav2 kernel.') group.add_argument('--disable_exllamav2', action='store_true', help='Disable ExLlamav2 kernel.')
# GPTQ-for-LLaMa
group = parser.add_argument_group('GPTQ-for-LLaMa')
group.add_argument('--wbits', type=int, default=0, help='Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.') group.add_argument('--wbits', type=int, default=0, help='Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.')
group.add_argument('--model_type', type=str, help='Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.')
group.add_argument('--groupsize', type=int, default=-1, help='Group size.') group.add_argument('--groupsize', type=int, default=-1, help='Group size.')
group.add_argument('--pre_layer', type=int, nargs='+', help='The number of layers to allocate to the GPU. Setting this parameter enables CPU offloading for 4-bit models. For multi-gpu, write the numbers separated by spaces, eg --pre_layer 30 60.')
group.add_argument('--checkpoint', type=str, help='The path to the quantized checkpoint file. If not specified, it will be automatically detected.') # AutoAWQ
group.add_argument('--monkey-patch', action='store_true', help='Apply the monkey patch for using LoRAs with quantized models.') group = parser.add_argument_group('AutoAWQ')
group.add_argument('--no_inject_fused_attention', action='store_true', help='Disable the use of fused attention, which will use less VRAM at the cost of slower inference.')
# HQQ # HQQ
group = parser.add_argument_group('HQQ') group = parser.add_argument_group('HQQ')
@ -206,7 +204,11 @@ group = parser.add_argument_group('Multimodal')
group.add_argument('--multimodal-pipeline', type=str, default=None, help='The multimodal pipeline to use. Examples: llava-7b, llava-13b.') group.add_argument('--multimodal-pipeline', type=str, default=None, help='The multimodal pipeline to use. Examples: llava-7b, llava-13b.')
# Deprecated parameters # Deprecated parameters
# group = parser.add_argument_group('Deprecated') group = parser.add_argument_group('Deprecated')
group.add_argument('--model_type', type=str, help='DEPRECATED')
group.add_argument('--pre_layer', type=int, nargs='+', help='DEPRECATED')
group.add_argument('--checkpoint', type=str, help='DEPRECATED')
group.add_argument('--monkey-patch', action='store_true', help='DEPRECATED')
args = parser.parse_args() args = parser.parse_args()
args_defaults = parser.parse_args([]) args_defaults = parser.parse_args([])
@ -251,8 +253,6 @@ def fix_loader_name(name):
return 'Transformers' return 'Transformers'
elif name in ['autogptq', 'auto-gptq', 'auto_gptq', 'auto gptq']: elif name in ['autogptq', 'auto-gptq', 'auto_gptq', 'auto gptq']:
return 'AutoGPTQ' return 'AutoGPTQ'
elif name in ['gptq-for-llama', 'gptqforllama', 'gptqllama', 'gptq for llama', 'gptq_for_llama']:
return 'GPTQ-for-LLaMa'
elif name in ['exllama', 'ex-llama', 'ex_llama', 'exlama']: elif name in ['exllama', 'ex-llama', 'ex_llama', 'exlama']:
return 'ExLlama' return 'ExLlama'
elif name in ['exllamav2', 'exllama-v2', 'ex_llama-v2', 'exlamav2', 'exlama-v2', 'exllama2', 'exllama-2']: elif name in ['exllamav2', 'exllama-v2', 'ex_llama-v2', 'exlamav2', 'exlama-v2', 'exllama2', 'exllama-2']:
@ -261,8 +261,6 @@ def fix_loader_name(name):
return 'ExLlamav2_HF' return 'ExLlamav2_HF'
elif name in ['autoawq', 'awq', 'auto-awq']: elif name in ['autoawq', 'awq', 'auto-awq']:
return 'AutoAWQ' return 'AutoAWQ'
elif name in ['quip#', 'quip-sharp', 'quipsharp', 'quip_sharp']:
return 'QuIP#'
elif name in ['hqq']: elif name in ['hqq']:
return 'HQQ' return 'HQQ'

48
modules/text_generation.py
View File

@ -16,6 +16,7 @@ from transformers import (
) )
import modules.shared as shared import modules.shared as shared
from modules import models
from modules.cache_utils import process_llamacpp_cache from modules.cache_utils import process_llamacpp_cache
from modules.callbacks import ( from modules.callbacks import (
Iteratorize, Iteratorize,
@ -27,15 +28,19 @@ from modules.grammar.grammar_utils import initialize_grammar
from modules.grammar.logits_process import GrammarConstrainedLogitsProcessor from modules.grammar.logits_process import GrammarConstrainedLogitsProcessor
from modules.html_generator import generate_basic_html from modules.html_generator import generate_basic_html
from modules.logging_colors import logger from modules.logging_colors import logger
from modules.models import clear_torch_cache from modules.models import clear_torch_cache, load_model
def generate_reply(*args, **kwargs): def generate_reply(*args, **kwargs):
if shared.args.idle_timeout > 0 and shared.model is None and shared.previous_model_name not in [None, 'None']:
shared.model, shared.tokenizer = load_model(shared.previous_model_name)
shared.generation_lock.acquire() shared.generation_lock.acquire()
try: try:
for result in _generate_reply(*args, **kwargs): for result in _generate_reply(*args, **kwargs):
yield result yield result
finally: finally:
models.last_generation_time = time.time()
shared.generation_lock.release() shared.generation_lock.release()
@ -56,8 +61,7 @@ def _generate_reply(question, state, stopping_strings=None, is_chat=False, escap
if generate_func != generate_reply_HF and shared.args.verbose: if generate_func != generate_reply_HF and shared.args.verbose:
logger.info("PROMPT=") logger.info("PROMPT=")
print(question) print_prompt(question)
print()
# Prepare the input # Prepare the input
original_question = question original_question = question
@ -134,9 +138,21 @@ def encode(prompt, add_special_tokens=True, add_bos_token=True, truncation_lengt
input_ids = np.array(input_ids).reshape(1, len(input_ids)) input_ids = np.array(input_ids).reshape(1, len(input_ids))
else: else:
input_ids = shared.tokenizer.encode(str(prompt), return_tensors='pt', add_special_tokens=add_special_tokens) input_ids = shared.tokenizer.encode(str(prompt), return_tensors='pt', add_special_tokens=add_special_tokens)
if not add_bos_token:
while len(input_ids[0]) > 0 and input_ids[0][0] == shared.tokenizer.bos_token_id: if hasattr(shared.tokenizer, 'bos_token_id'):
input_ids = input_ids[:, 1:] if add_bos_token:
if (len(input_ids[0]) > 0 and input_ids[0][0] != shared.tokenizer.bos_token_id) or len(input_ids[0]) == 0:
# Add a missing bos token (it may not have been added due to faulty model metadata)
bos_tensor = torch.tensor([[shared.tokenizer.bos_token_id]])
input_ids = torch.cat((bos_tensor, input_ids), 1)
# Prevent double bos token due to jinja templates with <s> somewhere
while len(input_ids[0]) > 1 and input_ids[0][0] == shared.tokenizer.bos_token_id and input_ids[0][1] == shared.tokenizer.bos_token_id:
input_ids = input_ids[:, 1:]
else:
# Remove any bos token that may have been added
while len(input_ids[0]) > 0 and input_ids[0][0] == shared.tokenizer.bos_token_id:
input_ids = input_ids[:, 1:]
# Handling truncation # Handling truncation
if truncation_length is not None: if truncation_length is not None:
@ -268,7 +284,7 @@ def get_reply_from_output_ids(output_ids, state=None, starting_from=0):
def generate_reply_HF(question, original_question, seed, state, stopping_strings=None, is_chat=False): def generate_reply_HF(question, original_question, seed, state, stopping_strings=None, is_chat=False):
generate_params = {} generate_params = {}
for k in ['max_new_tokens', 'temperature', 'temperature_last', 'dynamic_temperature', 'dynatemp_low', 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', 'smoothing_curve', 'top_p', 'min_p', 'top_k', 'repetition_penalty', 'presence_penalty', 'frequency_penalty', 'repetition_penalty_range', 'typical_p', 'tfs', 'top_a', 'guidance_scale', 'penalty_alpha', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta', 'do_sample', 'encoder_repetition_penalty', 'no_repeat_ngram_size']: for k in ['max_new_tokens', 'temperature', 'temperature_last', 'dynamic_temperature', 'dynatemp_low', 'dynatemp_high', 'dynatemp_exponent', 'smoothing_factor', 'smoothing_curve', 'top_p', 'min_p', 'top_k', 'repetition_penalty', 'presence_penalty', 'frequency_penalty', 'repetition_penalty_range', 'typical_p', 'tfs', 'top_a', 'guidance_scale', 'penalty_alpha', 'mirostat_mode', 'mirostat_tau', 'mirostat_eta', 'do_sample', 'encoder_repetition_penalty', 'no_repeat_ngram_size', 'dry_multiplier', 'dry_base', 'dry_allowed_length', 'dry_sequence_breakers']:
if k in state: if k in state:
generate_params[k] = state[k] generate_params[k] = state[k]
@ -343,8 +359,7 @@ def generate_reply_HF(question, original_question, seed, state, stopping_strings
print() print()
logger.info("PROMPT=") logger.info("PROMPT=")
print(decode(input_ids[0], skip_special_tokens=False)) print_prompt(decode(input_ids[0], skip_special_tokens=False))
print()
# Handle StreamingLLM for llamacpp_HF # Handle StreamingLLM for llamacpp_HF
if shared.model.__class__.__name__ == 'LlamacppHF' and shared.args.streaming_llm: if shared.model.__class__.__name__ == 'LlamacppHF' and shared.args.streaming_llm:
@ -433,3 +448,18 @@ def generate_reply_custom(question, original_question, seed, state, stopping_str
new_tokens = len(encode(original_question + reply)[0]) - original_tokens new_tokens = len(encode(original_question + reply)[0]) - original_tokens
print(f'Output generated in {(t1-t0):.2f} seconds ({new_tokens/(t1-t0):.2f} tokens/s, {new_tokens} tokens, context {original_tokens}, seed {seed})') print(f'Output generated in {(t1-t0):.2f} seconds ({new_tokens/(t1-t0):.2f} tokens/s, {new_tokens} tokens, context {original_tokens}, seed {seed})')
return return
def print_prompt(prompt, max_chars=2000):
DARK_YELLOW = "\033[38;5;3m"
RESET = "\033[0m"
if len(prompt) > max_chars:
half_chars = max_chars // 2
hidden_len = len(prompt[half_chars:-half_chars])
hidden_msg = f"{DARK_YELLOW}[...{hidden_len} characters hidden...]{RESET}"
print(prompt[:half_chars] + hidden_msg + prompt[-half_chars:])
else:
print(prompt)
print()

19
modules/training.py
View File

@ -292,12 +292,6 @@ def calc_trainable_parameters(model):
def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en: bool, k_proj_en: bool, o_proj_en: bool, gate_proj_en: bool, down_proj_en: bool, up_proj_en: bool, save_steps: int, micro_batch_size: int, batch_size: int, epochs: int, learning_rate: str, lr_scheduler_type: str, lora_rank: int, lora_alpha: int, lora_dropout: float, cutoff_len: int, dataset: str, eval_dataset: str, format: str, eval_steps: int, raw_text_file: str, overlap_len: int, newline_favor_len: int, higher_rank_limit: bool, warmup_steps: int, optimizer: str, hard_cut_string: str, train_only_after: str, stop_at_loss: float, add_eos_token: bool, min_chars: int, report_to: str): def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en: bool, k_proj_en: bool, o_proj_en: bool, gate_proj_en: bool, down_proj_en: bool, up_proj_en: bool, save_steps: int, micro_batch_size: int, batch_size: int, epochs: int, learning_rate: str, lr_scheduler_type: str, lora_rank: int, lora_alpha: int, lora_dropout: float, cutoff_len: int, dataset: str, eval_dataset: str, format: str, eval_steps: int, raw_text_file: str, overlap_len: int, newline_favor_len: int, higher_rank_limit: bool, warmup_steps: int, optimizer: str, hard_cut_string: str, train_only_after: str, stop_at_loss: float, add_eos_token: bool, min_chars: int, report_to: str):
if shared.args.monkey_patch:
from alpaca_lora_4bit.monkeypatch.peft_tuners_lora_monkey_patch import (
replace_peft_model_with_int4_lora_model
)
replace_peft_model_with_int4_lora_model()
global WANT_INTERRUPT global WANT_INTERRUPT
WANT_INTERRUPT = False WANT_INTERRUPT = False
@ -329,10 +323,6 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
time.sleep(5) time.sleep(5)
if shared.args.loader == 'GPTQ-for-LLaMa' and not shared.args.monkey_patch:
yield "LoRA training with GPTQ-for-LLaMa requires loading with `--monkey-patch`"
return
if cutoff_len <= 0 or micro_batch_size <= 0 or batch_size <= 0 or actual_lr <= 0 or lora_rank <= 0 or lora_alpha <= 0: if cutoff_len <= 0 or micro_batch_size <= 0 or batch_size <= 0 or actual_lr <= 0 or lora_rank <= 0 or lora_alpha <= 0:
yield "Cannot input zeroes." yield "Cannot input zeroes."
return return
@ -553,15 +543,6 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
yield traceback.format_exc().replace('\n', '\n\n') yield traceback.format_exc().replace('\n', '\n\n')
return return
if shared.args.monkey_patch:
from alpaca_lora_4bit.autograd_4bit import Autograd4bitQuantLinear
from alpaca_lora_4bit.models import Linear4bitLt
for _, m in lora_model.named_modules():
if isinstance(m, Autograd4bitQuantLinear) or isinstance(m, Linear4bitLt):
if m.is_v1_model:
m.zeros = m.zeros.half()
m.scales = m.scales.half()
class Tracked(): class Tracked():
def __init__(self): def __init__(self):
self.current_steps = 0 self.current_steps = 0

5
modules/ui.py
View File

@ -70,7 +70,6 @@ def list_model_elements():
'use_double_quant', 'use_double_quant',
'wbits', 'wbits',
'groupsize', 'groupsize',
'model_type',
'pre_layer', 'pre_layer',
'triton', 'triton',
'desc_act', 'desc_act',
@ -147,6 +146,10 @@ def list_interface_input_elements():
'repetition_penalty_range', 'repetition_penalty_range',
'encoder_repetition_penalty', 'encoder_repetition_penalty',
'no_repeat_ngram_size', 'no_repeat_ngram_size',
'dry_multiplier',
'dry_base',
'dry_allowed_length',
'dry_sequence_breakers',
'do_sample', 'do_sample',
'penalty_alpha', 'penalty_alpha',
'mirostat_mode', 'mirostat_mode',

22
modules/ui_model_menu.py
View File

@ -97,11 +97,10 @@ def create_ui():
shared.gradio['n_ctx'] = gr.Slider(minimum=0, maximum=shared.settings['truncation_length_max'], step=256, label="n_ctx", value=shared.args.n_ctx, info='Context length. Try lowering this if you run out of memory while loading the model.') shared.gradio['n_ctx'] = gr.Slider(minimum=0, maximum=shared.settings['truncation_length_max'], step=256, label="n_ctx", value=shared.args.n_ctx, info='Context length. Try lowering this if you run out of memory while loading the model.')
shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='List of proportions to split the model across multiple GPUs. Example: 18,17') shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='List of proportions to split the model across multiple GPUs. Example: 18,17')
shared.gradio['n_batch'] = gr.Slider(label="n_batch", minimum=1, maximum=2048, step=1, value=shared.args.n_batch) shared.gradio['n_batch'] = gr.Slider(label="n_batch", minimum=1, maximum=2048, step=1, value=shared.args.n_batch)
shared.gradio['threads'] = gr.Slider(label="threads", minimum=0, step=1, maximum=32, value=shared.args.threads) shared.gradio['threads'] = gr.Slider(label="threads", minimum=0, step=1, maximum=256, value=shared.args.threads)
shared.gradio['threads_batch'] = gr.Slider(label="threads_batch", minimum=0, step=1, maximum=32, value=shared.args.threads_batch) shared.gradio['threads_batch'] = gr.Slider(label="threads_batch", minimum=0, step=1, maximum=256, value=shared.args.threads_batch)
shared.gradio['wbits'] = gr.Dropdown(label="wbits", choices=["None", 1, 2, 3, 4, 8], value=shared.args.wbits if shared.args.wbits > 0 else "None") shared.gradio['wbits'] = gr.Dropdown(label="wbits", choices=["None", 1, 2, 3, 4, 8], value=shared.args.wbits if shared.args.wbits > 0 else "None")
shared.gradio['groupsize'] = gr.Dropdown(label="groupsize", choices=["None", 32, 64, 128, 1024], value=shared.args.groupsize if shared.args.groupsize > 0 else "None") shared.gradio['groupsize'] = gr.Dropdown(label="groupsize", choices=["None", 32, 64, 128, 1024], value=shared.args.groupsize if shared.args.groupsize > 0 else "None")
shared.gradio['model_type'] = gr.Dropdown(label="model_type", choices=["None"], value=shared.args.model_type or "None")
shared.gradio['pre_layer'] = gr.Slider(label="pre_layer", minimum=0, maximum=100, value=shared.args.pre_layer[0] if shared.args.pre_layer is not None else 0) shared.gradio['pre_layer'] = gr.Slider(label="pre_layer", minimum=0, maximum=100, value=shared.args.pre_layer[0] if shared.args.pre_layer is not None else 0)
shared.gradio['gpu_split'] = gr.Textbox(label='gpu-split', info='Comma-separated list of VRAM (in GB) to use per GPU. Example: 20,7,7') shared.gradio['gpu_split'] = gr.Textbox(label='gpu-split', info='Comma-separated list of VRAM (in GB) to use per GPU. Example: 20,7,7')
shared.gradio['max_seq_len'] = gr.Slider(label='max_seq_len', minimum=0, maximum=shared.settings['truncation_length_max'], step=256, info='Context length. Try lowering this if you run out of memory while loading the model.', value=shared.args.max_seq_len) shared.gradio['max_seq_len'] = gr.Slider(label='max_seq_len', minimum=0, maximum=shared.settings['truncation_length_max'], step=256, info='Context length. Try lowering this if you run out of memory while loading the model.', value=shared.args.max_seq_len)
@ -111,7 +110,6 @@ def create_ui():
shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.', value=shared.args.compress_pos_emb) shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.', value=shared.args.compress_pos_emb)
shared.gradio['autogptq_info'] = gr.Markdown('ExLlamav2_HF is recommended over AutoGPTQ for models derived from Llama.') shared.gradio['autogptq_info'] = gr.Markdown('ExLlamav2_HF is recommended over AutoGPTQ for models derived from Llama.')
shared.gradio['quipsharp_info'] = gr.Markdown('QuIP# has to be installed manually at the moment.')
with gr.Column(): with gr.Column():
shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit) shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)
@ -187,9 +185,7 @@ def create_ui():
def create_event_handlers(): def create_event_handlers():
shared.gradio['loader'].change( shared.gradio['loader'].change(loaders.make_loader_params_visible, gradio('loader'), gradio(loaders.get_all_params()))
loaders.make_loader_params_visible, gradio('loader'), gradio(loaders.get_all_params())).then(
lambda value: gr.update(choices=loaders.get_model_types(value)), gradio('loader'), gradio('model_type'))
# In this event handler, the interface state is read and updated # In this event handler, the interface state is read and updated
# with the model defaults (if any), and then the model is loaded # with the model defaults (if any), and then the model is loaded
@ -273,6 +269,10 @@ def load_lora_wrapper(selected_loras):
def download_model_wrapper(repo_id, specific_file, progress=gr.Progress(), return_links=False, check=False): def download_model_wrapper(repo_id, specific_file, progress=gr.Progress(), return_links=False, check=False):
try: try:
if repo_id == "":
yield ("Please enter a model path")
return
downloader = importlib.import_module("download-model").ModelDownloader() downloader = importlib.import_module("download-model").ModelDownloader()
progress(0.0) progress(0.0)
@ -290,7 +290,13 @@ def download_model_wrapper(repo_id, specific_file, progress=gr.Progress(), retur
return return
yield ("Getting the output folder") yield ("Getting the output folder")
output_folder = downloader.get_output_folder(model, branch, is_lora, is_llamacpp=is_llamacpp) output_folder = downloader.get_output_folder(
model,
branch,
is_lora,
is_llamacpp=is_llamacpp,
model_dir=shared.args.model_dir if shared.args.model_dir != shared.args_defaults.model_dir else None
)
if output_folder == Path("models"): if output_folder == Path("models"):
output_folder = Path(shared.args.model_dir) output_folder = Path(shared.args.model_dir)

8
modules/ui_parameters.py
View File

@ -38,6 +38,14 @@ def create_ui(default_preset):
shared.gradio['presence_penalty'] = gr.Slider(0, 2, value=generate_params['presence_penalty'], step=0.05, label='presence_penalty') shared.gradio['presence_penalty'] = gr.Slider(0, 2, value=generate_params['presence_penalty'], step=0.05, label='presence_penalty')
shared.gradio['repetition_penalty_range'] = gr.Slider(0, 4096, step=64, value=generate_params['repetition_penalty_range'], label='repetition_penalty_range') shared.gradio['repetition_penalty_range'] = gr.Slider(0, 4096, step=64, value=generate_params['repetition_penalty_range'], label='repetition_penalty_range')
shared.gradio['do_sample'] = gr.Checkbox(value=generate_params['do_sample'], label='do_sample') shared.gradio['do_sample'] = gr.Checkbox(value=generate_params['do_sample'], label='do_sample')
with gr.Blocks():
gr.Markdown("[DRY sequence repetition penalty](https://github.com/oobabooga/text-generation-webui/pull/5677)")
shared.gradio['dry_multiplier'] = gr.Slider(0, 5, value=generate_params['dry_multiplier'], step=0.01, label='dry_multiplier', info='Set to value > 0 to enable DRY. Controls the magnitude of the penalty for the shortest penalized sequences.')
shared.gradio['dry_base'] = gr.Slider(1, 4, value=generate_params['dry_base'], step=0.01, label='dry_base', info='Controls how fast the penalty grows with increasing sequence length.')
shared.gradio['dry_allowed_length'] = gr.Slider(1, 20, value=generate_params['dry_allowed_length'], step=1, label='dry_allowed_length', info='Longest sequence that can be repeated without being penalized.')
shared.gradio['dry_sequence_breakers'] = gr.Textbox(value=generate_params['dry_sequence_breakers'], label='dry_sequence_breakers', info='Tokens across which sequence matching is not continued. Specified as a comma-separated list of quoted strings.')
gr.Markdown("[Learn more](https://github.com/oobabooga/text-generation-webui/wiki/03-%E2%80%90-Parameters-Tab)") gr.Markdown("[Learn more](https://github.com/oobabooga/text-generation-webui/wiki/03-%E2%80%90-Parameters-Tab)")
with gr.Column(): with gr.Column():

2
one_click.py
View File

@ -388,7 +388,7 @@ def update_requirements(initial_installation=False, pull=True):
# Prepare the requirements file # Prepare the requirements file
textgen_requirements = open(requirements_file).read().splitlines() textgen_requirements = open(requirements_file).read().splitlines()
if is_cuda118: if is_cuda118:
textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements] textgen_requirements = [req.replace('+cu121', '+cu118').replace('+cu122', '+cu118') for req in textgen_requirements if "auto-gptq" not in req]
if is_windows() and is_cuda118: # No flash-attention on Windows for CUDA 11 if is_windows() and is_cuda118: # No flash-attention on Windows for CUDA 11
textgen_requirements = [req for req in textgen_requirements if 'oobabooga/flash-attention' not in req] textgen_requirements = [req for req in textgen_requirements if 'oobabooga/flash-attention' not in req]

43
requirements.txt
View File

@ -1,11 +1,12 @@
accelerate==0.27.* accelerate==0.30.*
aqlm[gpu,cpu]==1.1.3; platform_system == "Linux" aqlm[gpu,cpu]==1.1.5; platform_system == "Linux"
auto-gptq==0.7.1
bitsandbytes==0.43.* bitsandbytes==0.43.*
colorama colorama
datasets datasets
einops einops
gradio==4.26.* gradio==4.26.*
hqq==0.1.5 hqq==0.1.7.post2
jinja2==3.1.2 jinja2==3.1.2
lm_eval==0.3.0 lm_eval==0.3.0
markdown markdown
@ -23,7 +24,7 @@ safetensors==0.4.*
scipy scipy
sentencepiece sentencepiece
tensorboard tensorboard
transformers==4.40.* transformers==4.41.*
tqdm tqdm
wandb wandb
@ -36,28 +37,24 @@ soundfile
openai-whisper openai-whisper
# llama-cpp-python (CPU only, AVX2) # llama-cpp-python (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
# llama-cpp-python (CUDA, no tensor cores) # llama-cpp-python (CUDA, no tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.73+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.75+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.73+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.75+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.73+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.75+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.73+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.75+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# llama-cpp-python (CUDA, tensor cores) # llama-cpp-python (CUDA, tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.73+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.73+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.73+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.73+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# CUDA wheels # CUDA wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
@ -67,8 +64,4 @@ https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" autoawq==0.2.5; platform_system == "Linux" or platform_system == "Windows"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
autoawq==0.2.3; platform_system == "Linux" or platform_system == "Windows"

26
requirements_amd.txt
View File

@ -1,9 +1,9 @@
accelerate==0.27.* accelerate==0.30.*
colorama colorama
datasets datasets
einops einops
gradio==4.26.* gradio==4.26.*
hqq==0.1.5 hqq==0.1.7.post2
jinja2==3.1.2 jinja2==3.1.2
lm_eval==0.3.0 lm_eval==0.3.0
markdown markdown
@ -21,7 +21,7 @@ safetensors==0.4.*
scipy scipy
sentencepiece sentencepiece
tensorboard tensorboard
transformers==4.40.* transformers==4.41.*
tqdm tqdm
wandb wandb
@ -32,20 +32,16 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama-cpp-python (CPU only, AVX2) # llama-cpp-python (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
# AMD wheels # AMD wheels
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.73+rocm5.6.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.75+rocm5.6.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.73+rocm5.6.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.2.75+rocm5.6.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.5/autoawq-0.2.5+rocm561-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.5/autoawq-0.2.5+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.3/autoawq-0.2.3+rocm561-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.3/autoawq-0.2.3+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

22
requirements_amd_noavx2.txt
View File

@ -1,9 +1,9 @@
accelerate==0.27.* accelerate==0.30.*
colorama colorama
datasets datasets
einops einops
gradio==4.26.* gradio==4.26.*
hqq==0.1.5 hqq==0.1.7.post2
jinja2==3.1.2 jinja2==3.1.2
lm_eval==0.3.0 lm_eval==0.3.0
markdown markdown
@ -21,7 +21,7 @@ safetensors==0.4.*
scipy scipy
sentencepiece sentencepiece
tensorboard tensorboard
transformers==4.40.* transformers==4.41.*
tqdm tqdm
wandb wandb
@ -32,18 +32,14 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama-cpp-python (CPU only, no AVX2) # llama-cpp-python (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
# AMD wheels # AMD wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.5/autoawq-0.2.5+rocm561-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+rocm5.6-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.5/autoawq-0.2.5+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.3/autoawq-0.2.3+rocm561-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/casper-hansen/AutoAWQ/releases/download/v0.2.3/autoawq-0.2.3+rocm561-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"

18
requirements_apple_intel.txt
View File

@ -1,9 +1,9 @@
accelerate==0.27.* accelerate==0.30.*
colorama colorama
datasets datasets
einops einops
gradio==4.26.* gradio==4.26.*
hqq==0.1.5 hqq==0.1.7.post2
jinja2==3.1.2 jinja2==3.1.2
lm_eval==0.3.0 lm_eval==0.3.0
markdown markdown
@ -21,7 +21,7 @@ safetensors==0.4.*
scipy scipy
sentencepiece sentencepiece
tensorboard tensorboard
transformers==4.40.* transformers==4.41.*
tqdm tqdm
wandb wandb
@ -32,10 +32,10 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp311-cp311-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_11_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp311-cp311-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_12_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl

22
requirements_apple_silicon.txt
View File

@ -1,9 +1,9 @@
accelerate==0.27.* accelerate==0.30.*
colorama colorama
datasets datasets
einops einops
gradio==4.26.* gradio==4.26.*
hqq==0.1.5 hqq==0.1.7.post2
jinja2==3.1.2 jinja2==3.1.2
lm_eval==0.3.0 lm_eval==0.3.0
markdown markdown
@ -21,7 +21,7 @@ safetensors==0.4.*
scipy scipy
sentencepiece sentencepiece
tensorboard tensorboard
transformers==4.40.* transformers==4.41.*
tqdm tqdm
wandb wandb
@ -32,12 +32,12 @@ sse-starlette==1.6.5
tiktoken tiktoken
# Mac wheels # Mac wheels
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp311-cp311-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_11_0_arm64.whl; platform_system == "Darwin" and platform_release >= "20.0.0" and platform_release < "21.0.0" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp311-cp311-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_12_0_arm64.whl; platform_system == "Darwin" and platform_release >= "21.0.0" and platform_release < "22.0.0" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp311-cp311-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.73-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.2.75-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20-py3-none-any.whl

14
requirements_cpu_only.txt
View File

@ -1,9 +1,9 @@
accelerate==0.27.* accelerate==0.30.*
colorama colorama
datasets datasets
einops einops
gradio==4.26.* gradio==4.26.*
hqq==0.1.5 hqq==0.1.7.post2
jinja2==3.1.2 jinja2==3.1.2
lm_eval==0.3.0 lm_eval==0.3.0
markdown markdown
@ -21,7 +21,7 @@ safetensors==0.4.*
scipy scipy
sentencepiece sentencepiece
tensorboard tensorboard
transformers==4.40.* transformers==4.41.*
tqdm tqdm
wandb wandb
@ -32,7 +32,7 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama-cpp-python (CPU only, AVX2) # llama-cpp-python (CPU only, AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx2-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

14
requirements_cpu_only_noavx2.txt
View File

@ -1,9 +1,9 @@
accelerate==0.27.* accelerate==0.30.*
colorama colorama
datasets datasets
einops einops
gradio==4.26.* gradio==4.26.*
hqq==0.1.5 hqq==0.1.7.post2
jinja2==3.1.2 jinja2==3.1.2
lm_eval==0.3.0 lm_eval==0.3.0
markdown markdown
@ -21,7 +21,7 @@ safetensors==0.4.*
scipy scipy
sentencepiece sentencepiece
tensorboard tensorboard
transformers==4.40.* transformers==4.41.*
tqdm tqdm
wandb wandb
@ -32,7 +32,7 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama-cpp-python (CPU only, no AVX2) # llama-cpp-python (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"

43
requirements_noavx2.txt
View File

@ -1,11 +1,12 @@
accelerate==0.27.* accelerate==0.30.*
aqlm[gpu,cpu]==1.1.3; platform_system == "Linux" aqlm[gpu,cpu]==1.1.5; platform_system == "Linux"
auto-gptq==0.7.1
bitsandbytes==0.43.* bitsandbytes==0.43.*
colorama colorama
datasets datasets
einops einops
gradio==4.26.* gradio==4.26.*
hqq==0.1.5 hqq==0.1.7.post2
jinja2==3.1.2 jinja2==3.1.2
lm_eval==0.3.0 lm_eval==0.3.0
markdown markdown
@ -23,7 +24,7 @@ safetensors==0.4.*
scipy scipy
sentencepiece sentencepiece
tensorboard tensorboard
transformers==4.40.* transformers==4.41.*
tqdm tqdm
wandb wandb
@ -34,28 +35,24 @@ sse-starlette==1.6.5
tiktoken tiktoken
# llama-cpp-python (CPU only, no AVX2) # llama-cpp-python (CPU only, no AVX2)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.73+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.2.75+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
# llama-cpp-python (CUDA, no tensor cores) # llama-cpp-python (CUDA, no tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.73+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.75+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.73+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.75+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.73+cu121avx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.75+cu121avx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.73+cu121avx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda-0.2.75+cu121avx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# llama-cpp-python (CUDA, tensor cores) # llama-cpp-python (CUDA, tensor cores)
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.73+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121avx-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.73+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121avx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.73+cu121avx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121avx-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.73+cu121avx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.2.75+cu121avx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# CUDA wheels # CUDA wheels
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/AutoGPTQ/releases/download/v0.6.0/auto_gptq-0.6.0+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/oobabooga/exllamav2/releases/download/v0.0.20/exllamav2-0.0.20+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
@ -65,8 +62,4 @@ https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn
https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10" https://github.com/oobabooga/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2.0cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11" https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10" https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.6/flash_attn-2.5.6+cu122torch2.2cxx11abiFALSE-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11" autoawq==0.2.5; platform_system == "Linux" or platform_system == "Windows"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/jllllll/GPTQ-for-LLaMa-CUDA/releases/download/0.1.1/gptq_for_llama-0.1.1+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
autoawq==0.2.3; platform_system == "Linux" or platform_system == "Windows"

6
requirements_nowheels.txt
View File

@ -1,9 +1,9 @@
accelerate==0.27.* accelerate==0.30.*
colorama colorama
datasets datasets
einops einops
gradio==4.26.* gradio==4.26.*
hqq==0.1.5 hqq==0.1.7.post2
jinja2==3.1.2 jinja2==3.1.2
lm_eval==0.3.0 lm_eval==0.3.0
markdown markdown
@ -21,7 +21,7 @@ safetensors==0.4.*
scipy scipy
sentencepiece sentencepiece
tensorboard tensorboard
transformers==4.40.* transformers==4.41.*
tqdm tqdm
wandb wandb

9
server.py
View File

@ -32,7 +32,7 @@ import sys
import time import time
from functools import partial from functools import partial
from pathlib import Path from pathlib import Path
from threading import Lock from threading import Lock, Thread
import yaml import yaml
@ -52,7 +52,7 @@ from modules import (
) )
from modules.extensions import apply_extensions from modules.extensions import apply_extensions
from modules.LoRA import add_lora_to_model from modules.LoRA import add_lora_to_model
from modules.models import load_model from modules.models import load_model, unload_model_if_idle
from modules.models_settings import ( from modules.models_settings import (
get_fallback_settings, get_fallback_settings,
get_model_metadata, get_model_metadata,
@ -245,6 +245,11 @@ if __name__ == "__main__":
shared.generation_lock = Lock() shared.generation_lock = Lock()
if shared.args.idle_timeout > 0:
timer_thread = Thread(target=unload_model_if_idle)
timer_thread.daemon = True
timer_thread.start()
if shared.args.nowebui: if shared.args.nowebui:
# Start the API in standalone mode # Start the API in standalone mode
shared.args.extensions = [x for x in shared.args.extensions if x != 'gallery'] shared.args.extensions = [x for x in shared.args.extensions if x != 'gallery']