Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-11-24 00:46:53 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'oobabooga:main' into main

Browse Source
This commit is contained in:
SDS 2023-04-01 21:02:24 +02:00 committed by GitHub
commit bdb2dfa02e
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 86 additions and 51 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

108
README.md
View File

@ -12,28 +12,28 @@ Its goal is to become the [AUTOMATIC1111/stable-diffusion-webui](https://github.
## Features ## Features
* Switch between different models using a dropdown menu. * Dropdown menu for switching between models
* Notebook mode that resembles OpenAI's playground. * Notebook mode that resembles OpenAI's playground
* Chat mode for conversation and role playing. * Chat mode for conversation and role playing
* Generate nice HTML output for GPT-4chan. * Nice HTML output for GPT-4chan
* Generate Markdown output for [GALACTICA](https://github.com/paperswithcode/galai), including LaTeX support. * Markdown output for [GALACTICA](https://github.com/paperswithcode/galai), including LaTeX rendering
* Support for [Pygmalion](https://huggingface.co/models?search=pygmalionai/pygmalion) and custom characters in JSON or TavernAI Character Card formats ([FAQ](https://github.com/oobabooga/text-generation-webui/wiki/Pygmalion-chat-model-FAQ)). * Custom chat characters in JSON format ([FAQ](https://github.com/oobabooga/text-generation-webui/wiki/Custom-characters-FAQ))
* Advanced chat features (send images, get audio responses with TTS). * Advanced chat features (send images, get audio responses with TTS)
* Stream the text output in real time very efficiently. * Very efficient text streaming
* Load parameter presets from text files. * Parameter presets
* Load large models in 8-bit mode. * 8-bit mode
* Split large models across your GPU(s), CPU, and disk. * Layers splitting across GPU(s), CPU, and disk
* CPU mode. * CPU mode
* [FlexGen offload](https://github.com/oobabooga/text-generation-webui/wiki/FlexGen). * [FlexGen](https://github.com/oobabooga/text-generation-webui/wiki/FlexGen)
* [DeepSpeed ZeRO-3 offload](https://github.com/oobabooga/text-generation-webui/wiki/DeepSpeed). * [DeepSpeed ZeRO-3](https://github.com/oobabooga/text-generation-webui/wiki/DeepSpeed)
* Get responses via API, [with](https://github.com/oobabooga/text-generation-webui/blob/main/api-example-streaming.py) or [without](https://github.com/oobabooga/text-generation-webui/blob/main/api-example.py) streaming. * API [with](https://github.com/oobabooga/text-generation-webui/blob/main/api-example-streaming.py) streaming and [without](https://github.com/oobabooga/text-generation-webui/blob/main/api-example.py) streaming
* [LLaMA model, including 4-bit GPTQ support](https://github.com/oobabooga/text-generation-webui/wiki/LLaMA-model). * [LLaMA model, including 4-bit GPTQ](https://github.com/oobabooga/text-generation-webui/wiki/LLaMA-model)
* [llama.cpp support](https://github.com/oobabooga/text-generation-webui/wiki/llama.cpp-models). **\*NEW!\*** * [llama.cpp](https://github.com/oobabooga/text-generation-webui/wiki/llama.cpp-models) **\*NEW!\***
* [RWKV model](https://github.com/oobabooga/text-generation-webui/wiki/RWKV-model). * [RWKV model](https://github.com/oobabooga/text-generation-webui/wiki/RWKV-model)
* [Supports LoRAs](https://github.com/oobabooga/text-generation-webui/wiki/Using-LoRAs). * [LoRa (loading and training)](https://github.com/oobabooga/text-generation-webui/wiki/Using-LoRAs)
* Supports softprompts. * Softprompts
* [Supports extensions](https://github.com/oobabooga/text-generation-webui/wiki/Extensions). * [Extensions](https://github.com/oobabooga/text-generation-webui/wiki/Extensions)
* [Works on Google Colab](https://github.com/oobabooga/text-generation-webui/wiki/Running-on-Colab). * [Google Colab](https://github.com/oobabooga/text-generation-webui/wiki/Running-on-Colab)
## Installation ## Installation
@ -62,9 +62,9 @@ Recommended if you have some experience with the command-line.
On Windows, I additionally recommend carrying out the installation on WSL instead of the base system: [WSL installation guide](https://github.com/oobabooga/text-generation-webui/wiki/Windows-Subsystem-for-Linux-(Ubuntu)-Installation-Guide). On Windows, I additionally recommend carrying out the installation on WSL instead of the base system: [WSL installation guide](https://github.com/oobabooga/text-generation-webui/wiki/Windows-Subsystem-for-Linux-(Ubuntu)-Installation-Guide).
#### 0. Install Conda 0. Install Conda
Conda can be downloaded here: https://docs.conda.io/en/latest/miniconda.html https://docs.conda.io/en/latest/miniconda.html
On Linux or WSL, it can be automatically installed with these two commands: On Linux or WSL, it can be automatically installed with these two commands:
@ -75,14 +75,14 @@ bash Miniconda3.sh
Source: https://educe-ubc.github.io/conda.html Source: https://educe-ubc.github.io/conda.html
#### 1. Create a new conda environment 1. Create a new conda environment
``` ```
conda create -n textgen python=3.10.9 conda create -n textgen python=3.10.9
conda activate textgen conda activate textgen
``` ```
#### 2. Install Pytorch 2. Install Pytorch
| System | GPU | Command | | System | GPU | Command |
|--------|---------|---------| |--------|---------|---------|
@ -95,7 +95,7 @@ The up to date commands can be found here: https://pytorch.org/get-started/local
MacOS users, refer to the comments here: https://github.com/oobabooga/text-generation-webui/pull/393 MacOS users, refer to the comments here: https://github.com/oobabooga/text-generation-webui/pull/393
#### 3. Install the web UI 3. Install the web UI
``` ```
git clone https://github.com/oobabooga/text-generation-webui git clone https://github.com/oobabooga/text-generation-webui
@ -120,27 +120,24 @@ https://github.com/oobabooga/text-generation-webui/issues/174, https://github.co
Models should be placed inside the `models` folder. Models should be placed inside the `models` folder.
[Hugging Face](https://huggingface.co/models?pipeline_tag=text-generation&sort=downloads) is the main place to download models. These are some noteworthy examples: [Hugging Face](https://huggingface.co/models?pipeline_tag=text-generation&sort=downloads) is the main place to download models. These are some examples:
* [Pythia](https://huggingface.co/models?search=eleutherai/pythia) * [Pythia](https://huggingface.co/models?sort=downloads&search=eleutherai%2Fpythia+deduped)
* [OPT](https://huggingface.co/models?search=facebook/opt) * [OPT](https://huggingface.co/models?search=facebook/opt)
* [GALACTICA](https://huggingface.co/models?search=facebook/galactica) * [GALACTICA](https://huggingface.co/models?search=facebook/galactica)
* [GPT-J 6B](https://huggingface.co/EleutherAI/gpt-j-6B/tree/main) * [GPT-J 6B](https://huggingface.co/EleutherAI/gpt-j-6B/tree/main)
* [GPT-Neo](https://huggingface.co/models?pipeline_tag=text-generation&sort=downloads&search=eleutherai+%2F+gpt-neo)
* [\*-Erebus](https://huggingface.co/models?search=erebus) (NSFW)
* [Pygmalion](https://huggingface.co/models?search=pygmalion) (NSFW)
You can automatically download a model from HF using the script `download-model.py`: You can automatically download a model from HF using the script `download-model.py`:
python download-model.py organization/model python download-model.py organization/model
For instance: For example:
python download-model.py facebook/opt-1.3b python download-model.py facebook/opt-1.3b
If you want to download a model manually, note that all you need are the json, txt, and pytorch\*.bin (or model*.safetensors) files. The remaining files are not necessary. If you want to download a model manually, note that all you need are the json, txt, and pytorch\*.bin (or model*.safetensors) files. The remaining files are not necessary.
### GPT-4chan #### GPT-4chan
[GPT-4chan](https://huggingface.co/ykilcher/gpt-4chan) has been shut down from Hugging Face, so you need to download it elsewhere. You have two options: [GPT-4chan](https://huggingface.co/ykilcher/gpt-4chan) has been shut down from Hugging Face, so you need to download it elsewhere. You have two options:
@ -169,10 +166,10 @@ Then browse to
`http://localhost:7860/?__theme=dark` `http://localhost:7860/?__theme=dark`
Optionally, you can use the following command-line flags: Optionally, you can use the following command-line flags:
#### Basic settings
| Flag | Description | | Flag | Description |
|------------------|-------------| |------------------|-------------|
| `-h`, `--help` | show this help message and exit | | `-h`, `--help` | show this help message and exit |
@ -187,29 +184,64 @@ Optionally, you can use the following command-line flags:
| `--settings SETTINGS_FILE` | Load the default interface settings from this json file. See `settings-template.json` for an example. If you create a file called `settings.json`, this file will be loaded by default without the need to use the `--settings` flag.| | `--settings SETTINGS_FILE` | Load the default interface settings from this json file. See `settings-template.json` for an example. If you create a file called `settings.json`, 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. | | `--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. | | `--verbose` | Print the prompts to the terminal. |
#### Accelerate/transformers
| Flag | Description |
|------------------|-------------|
| `--cpu` | Use the CPU to generate text.| | `--cpu` | Use the CPU to generate text.|
| `--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 ...]` | Maxmimum 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`. | | `--gpu-memory GPU_MEMORY [GPU_MEMORY ...]` | Maxmimum 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`. |
| `--cpu-memory CPU_MEMORY` | Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.| | `--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.| | `--load-in-8bit` | Load the model with 8-bit precision.|
| `--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 the VRAM usage a bit with a performance cost. | | `--no-cache` | Set `use_cache` to False while generating text. This reduces the VRAM usage a bit with a performance cost. |
#### llama.cpp
| Flag | Description |
|------------------|-------------|
| `--threads` | Number of threads to use in llama.cpp. | | `--threads` | Number of threads to use in llama.cpp. |
#### GPTQ
| Flag | Description |
|------------------|-------------|
| `--wbits WBITS` | GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. | | `--wbits WBITS` | GPTQ: Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. |
| `--model_type MODEL_TYPE` | GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported. | | `--model_type MODEL_TYPE` | GPTQ: Model type of pre-quantized model. Currently LLaMA, OPT, and GPT-J are supported. |
| `--groupsize GROUPSIZE` | GPTQ: Group size. | | `--groupsize GROUPSIZE` | GPTQ: Group size. |
| `--pre_layer PRE_LAYER` | GPTQ: The number of layers to preload. | | `--pre_layer PRE_LAYER` | GPTQ: The number of layers to preload. |
#### FlexGen
| Flag | Description |
|------------------|-------------|
| `--flexgen` | Enable the use of FlexGen offloading. | | `--flexgen` | Enable the use of FlexGen offloading. |
| `--percent PERCENT [PERCENT ...]` | FlexGen: allocation percentages. Must be 6 numbers separated by spaces (default: 0, 100, 100, 0, 100, 0). | | `--percent PERCENT [PERCENT ...]` | FlexGen: allocation percentages. Must be 6 numbers separated by spaces (default: 0, 100, 100, 0, 100, 0). |
| `--compress-weight` | FlexGen: Whether to compress weight (default: False).| | `--compress-weight` | FlexGen: Whether to compress weight (default: False).|
| `--pin-weight [PIN_WEIGHT]` | FlexGen: whether to pin weights (setting this to False reduces CPU memory by 20%). | | `--pin-weight [PIN_WEIGHT]` | FlexGen: whether to pin weights (setting this to False reduces CPU memory by 20%). |
#### DeepSpeed
| Flag | Description |
|------------------|-------------|
| `--deepspeed` | Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration. | | `--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. | | `--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. | | `--local_rank LOCAL_RANK` | DeepSpeed: Optional argument for distributed setups. |
#### RWKV
| Flag | Description |
|------------------|-------------|
| `--rwkv-strategy RWKV_STRATEGY` | RWKV: The strategy to use while loading the model. Examples: "cpu fp32", "cuda fp16", "cuda fp16i8". | | `--rwkv-strategy RWKV_STRATEGY` | RWKV: The strategy to use while loading the model. Examples: "cpu fp32", "cuda fp16", "cuda fp16i8". |
| `--rwkv-cuda-on` | RWKV: Compile the CUDA kernel for better performance. | | `--rwkv-cuda-on` | RWKV: Compile the CUDA kernel for better performance. |
#### Gradio
| Flag | Description |
|------------------|-------------|
| `--listen` | Make the web UI reachable from your local network. | | `--listen` | Make the web UI reachable from your local network. |
| `--listen-port LISTEN_PORT` | The listening port that the server will use. | | `--listen-port LISTEN_PORT` | The listening port that the server will use. |
| `--share` | Create a public URL. This is useful for running the web UI on Google Colab or similar. | | `--share` | Create a public URL. This is useful for running the web UI on Google Colab or similar. |
@ -224,6 +256,8 @@ Inference settings presets can be created under `presets/` as text files. These
By default, 10 presets by NovelAI and KoboldAI are included. These were selected out of a sample of 43 presets after applying a K-Means clustering algorithm and selecting the elements closest to the average of each cluster. By default, 10 presets by NovelAI and KoboldAI are included. These were selected out of a sample of 43 presets after applying a K-Means clustering algorithm and selecting the elements closest to the average of each cluster.
[Visualization](https://user-images.githubusercontent.com/112222186/228956352-1addbdb9-2456-465a-b51d-089f462cd385.png)
## System requirements ## System requirements
Check the [wiki](https://github.com/oobabooga/text-generation-webui/wiki/System-requirements) for some examples of VRAM and RAM usage in both GPU and CPU mode. Check the [wiki](https://github.com/oobabooga/text-generation-webui/wiki/System-requirements) for some examples of VRAM and RAM usage in both GPU and CPU mode.

23
download-model.py
View File

@ -63,16 +63,17 @@ def sanitize_branch_name(branch_name):
def select_model_from_default_options(): def select_model_from_default_options():
models = { models = {
"Pygmalion 6B original": ("PygmalionAI", "pygmalion-6b", "b8344bb4eb76a437797ad3b19420a13922aaabe1"), "OPT 6.7B": ("facebook", "opt-6.7b", "main"),
"Pygmalion 6B main": ("PygmalionAI", "pygmalion-6b", "main"), "OPT 2.7B": ("facebook", "opt-2.7b", "main"),
"Pygmalion 6B dev": ("PygmalionAI", "pygmalion-6b", "dev"), "OPT 1.3B": ("facebook", "opt-1.3b", "main"),
"Pygmalion 2.7B": ("PygmalionAI", "pygmalion-2.7b", "main"), "OPT 350M": ("facebook", "opt-350m", "main"),
"Pygmalion 1.3B": ("PygmalionAI", "pygmalion-1.3b", "main"), "GALACTICA 6.7B": ("facebook", "galactica-6.7b", "main"),
"Pygmalion 350m": ("PygmalionAI", "pygmalion-350m", "main"), "GALACTICA 1.3B": ("facebook", "galactica-1.3b", "main"),
"OPT 6.7b": ("facebook", "opt-6.7b", "main"), "GALACTICA 125M": ("facebook", "galactica-125m", "main"),
"OPT 2.7b": ("facebook", "opt-2.7b", "main"), "Pythia-6.9B-deduped": ("EleutherAI", "pythia-6.9b-deduped", "main"),
"OPT 1.3b": ("facebook", "opt-1.3b", "main"), "Pythia-2.8B-deduped": ("EleutherAI", "pythia-2.8b-deduped", "main"),
"OPT 350m": ("facebook", "opt-350m", "main"), "Pythia-1.4B-deduped": ("EleutherAI", "pythia-1.4b-deduped", "main"),
"Pythia-410M-deduped": ("EleutherAI", "pythia-410m-deduped", "main"),
} }
choices = {} choices = {}
@ -91,8 +92,8 @@ def select_model_from_default_options():
print("""\nThen type the name of your desired Hugging Face model in the format organization/name. print("""\nThen type the name of your desired Hugging Face model in the format organization/name.
Examples: Examples:
PygmalionAI/pygmalion-6b
facebook/opt-1.3b facebook/opt-1.3b
EleutherAI/pythia-1.4b-deduped
""") """)
print("Input> ", end='') print("Input> ", end='')

4
modules/shared.py
View File

@ -86,8 +86,8 @@ parser.add_argument('--verbose', action='store_true', help='Print the prompts to
# Accelerate/transformers # Accelerate/transformers
parser.add_argument('--cpu', action='store_true', help='Use the CPU to generate text.') parser.add_argument('--cpu', action='store_true', help='Use the CPU to generate text.')
parser.add_argument('--auto-devices', action='store_true', help='Automatically split the model across the available GPU(s) and CPU.') parser.add_argument('--auto-devices', action='store_true', help='Automatically split the model across the available GPU(s) and CPU.')
parser.add_argument('--gpu-memory', type=str, nargs="+", help='Maxmimum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs.') parser.add_argument('--gpu-memory', type=str, nargs="+", help='Maxmimum 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.')
parser.add_argument('--cpu-memory', type=str, help='Maximum CPU memory in GiB to allocate for offloaded weights. Must be an integer number. Defaults to 99.') parser.add_argument('--cpu-memory', type=str, help='Maximum CPU memory in GiB to allocate for offloaded weights. Same as above.')
parser.add_argument('--disk', action='store_true', help='If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.') parser.add_argument('--disk', action='store_true', help='If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.')
parser.add_argument('--disk-cache-dir', type=str, default="cache", help='Directory to save the disk cache to. Defaults to "cache".') parser.add_argument('--disk-cache-dir', type=str, default="cache", help='Directory to save the disk cache to. Defaults to "cache".')
parser.add_argument('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision.') parser.add_argument('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision.')