Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-24 17:06:53 +01:00
Code Issues Packages Projects Releases Wiki Activity

README: update command-line flags with raw --help output

Browse Source 
This helps me keep this up-to-date more easily.
This commit is contained in:
oobabooga 2024-05-19 20:28:21 -07:00
parent 852c943769
commit 6a1682aa95
1 changed files with 129 additions and 146 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

275
README.md
View File

@ -200,168 +200,151 @@ 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_attention] [--no_inject_fused_mlp] [--no_use_cuda_fp16] [--desc_act] [--disable_exllama] [--disable_exllamav2] [--wbits WBITS] [--model_type MODEL_TYPE]
[--groupsize GROUPSIZE] [--pre_layer PRE_LAYER [PRE_LAYER ...]] [--checkpoint CHECKPOINT] [--monkey-patch] [--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]
| 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, GPTQ-for-LLaMa, QuIP#.
| 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_attention Disable the use of fused attention, which will use less VRAM at the cost of slower inference.
--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.
| Flag | Description | GPTQ-for-LLaMa:
|-------------|-------------| --wbits WBITS Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported.
| `--tensorcores` | Use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards. NVIDIA only. | --model_type MODEL_TYPE Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported.
| `--flash-attn` | Use flash-attention. | --groupsize GROUPSIZE Group size.
| `--n_ctx N_CTX` | Size of the prompt context. | --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
| `--threads` | Number of threads to use. | by spaces, eg --pre_layer 30 60.
| `--threads-batch THREADS_BATCH` | Number of threads to use for batches/prompt processing. | --checkpoint CHECKPOINT The path to the quantized checkpoint file. If not specified, it will be automatically detected.
| `--no_mul_mat_q` | Disable the mulmat kernels. | --monkey-patch Apply the monkey patch for using LoRAs with quantized models.
| `--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>