Welcome to my GitHub repository! 🚀 My name is AdekaBot, and I am an AI assistant developed by Özgür Sarıgül. I'm here to help answer any questions you may have about me or my capabilities.
About Me 🤖 I was created through a combination of natural language processing (NLP) and machine learning techniques. My primary function is to understand and respond to user input in a helpful and informative manner. Whether you want to know more about me or just want to chat, feel free to ask!
- 3 interface modes: default (two columns), notebook, and chat
- Multiple model backends: transformers, llama.cpp, ExLlama, AutoGPTQ, GPTQ-for-LLaMa, ctransformers
- Dropdown menu for quickly switching between different models
- LoRA: load and unload LoRAs on the fly, train a new LoRA using QLoRA
- Precise instruction templates for chat mode, including Llama-2-chat, Alpaca, Vicuna, WizardLM, StableLM, and many others
- 4-bit, 8-bit, and CPU inference through the transformers library
- Use llama.cpp models with transformers samplers (
llamacpp_HFloader) - Multimodal pipelines, including LLaVA and MiniGPT-4
- Extensions framework
- Custom chat characters
- Very efficient text streaming
- Markdown output with LaTeX rendering, to use for instance with GALACTICA
- API, including endpoints for websocket streaming (see the examples)
%cd /content
!apt-get -y install -qq aria2
!git clone https://github.com/adeka299aaa/AdekaBot
%cd /content/AdekaBot
!pip install -r requirements.txt
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/4bit/Llama-2-7b-chat-hf/resolve/main/model-00001-of-00002.safetensors -d /content/AdekaBot/models/Llama-2-7b-chat-hf -o model-00001-of-00002.safetensors
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/4bit/Llama-2-7b-chat-hf/resolve/main/model-00002-of-00002.safetensors -d /content/AdekaBot/models/Llama-2-7b-chat-hf -o model-00002-of-00002.safetensors
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/4bit/Llama-2-7b-chat-hf/raw/main/model.safetensors.index.json -d /content/AdekaBot/models/Llama-2-7b-chat-hf -o model.safetensors.index.json
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/4bit/Llama-2-7b-chat-hf/raw/main/special_tokens_map.json -d /content/AdekaBot/models/Llama-2-7b-chat-hf -o special_tokens_map.json
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/4bit/Llama-2-7b-chat-hf/resolve/main/tokenizer.model -d /content/AdekaBot/models/Llama-2-7b-chat-hf -o tokenizer.model
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/4bit/Llama-2-7b-chat-hf/raw/main/tokenizer_config.json -d /content/AdekaBot/models/Llama-2-7b-chat-hf -o tokenizer_config.json
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/4bit/Llama-2-7b-chat-hf/raw/main/config.json -d /content/AdekaBot/models/Llama-2-7b-chat-hf -o config.json
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/4bit/Llama-2-7b-chat-hf/raw/main/generation_config.json -d /content/AdekaBot/models/Llama-2-7b-chat-hf -o generation_config.json
%cd /content/AdekaBot
!python server.py --share --chat --model /content/AdekaBot/models/Llama-2-7b-chat-hf
| Windows | Linux | macOS | WSL |
|---|---|---|---|
| oobabooga-windows.zip | oobabooga-linux.zip | oobabooga-macos.zip | oobabooga-wsl.zip |
Just download the zip above, extract it, and double-click on "start". The web UI and all its dependencies will be installed in the same folder.
- The source codes and more information can be found here: https://github.com/oobabooga/one-click-installers
- There is no need to run the installers as admin.
Recommended if you have some experience with the command-line.
https://docs.conda.io/en/latest/miniconda.html
On Linux or WSL, it can be automatically installed with these two commands (source):
curl -sL "https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh" > "Miniconda3.sh"
bash Miniconda3.sh
conda create -n textgen python=3.10.9
conda activate textgen
| System | GPU | Command |
|---|---|---|
| Linux/WSL | NVIDIA | pip3 install torch torchvision torchaudio |
| Linux/WSL | CPU only | pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu |
| Linux | AMD | pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/rocm5.4.2 |
| MacOS + MPS | Any | pip3 install torch torchvision torchaudio |
| Windows | NVIDIA | pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu117 |
| Windows | CPU only | pip3 install torch torchvision torchaudio |
The up-to-date commands can be found here: https://pytorch.org/get-started/locally/.
- MacOS users: oobabooga/text-generation-webui#393
- AMD users: https://rentry.org/eq3hg
Precompiled wheels are included for CPU-only and NVIDIA GPUs (cuBLAS). For AMD, Metal, and some specific CPUs, you need to uninstall those wheels and compile llama-cpp-python yourself.
To uninstall:
pip uninstall -y llama-cpp-python llama-cpp-python-cuda
To compile: https://github.com/abetlen/llama-cpp-python#installation-with-openblas--cublas--clblast--metal
bitsandbytes >= 0.39 may not work. In that case, to use --load-in-8bit, you may have to downgrade like this:
- Linux:
pip install bitsandbytes==0.38.1 - Windows:
pip install https://github.com/jllllll/bitsandbytes-windows-webui/raw/main/bitsandbytes-0.38.1-py3-none-any.whl
ln -s docker/{Dockerfile,docker-compose.yml,.dockerignore} .
cp docker/.env.example .env
# Edit .env and set TORCH_CUDA_ARCH_LIST based on your GPU model
docker compose up --build
- You need to have docker compose v2.17 or higher installed. See this guide for instructions.
- For additional docker files, check out this repository.
From time to time, the requirements.txt changes. To update, use these commands:
conda activate textgen
cd text-generation-webui
pip install -r requirements.txt --upgrade
Models should be placed in the text-generation-webui/models folder. They are usually downloaded from Hugging Face.
- Transformers or GPTQ models are made of several files and must be placed in a subfolder. Example:
text-generation-webui
├── models
│ ├── lmsys_vicuna-33b-v1.3
│ │ ├── config.json
│ │ ├── generation_config.json
│ │ ├── pytorch_model-00001-of-00007.bin
│ │ ├── pytorch_model-00002-of-00007.bin
│ │ ├── pytorch_model-00003-of-00007.bin
│ │ ├── pytorch_model-00004-of-00007.bin
│ │ ├── pytorch_model-00005-of-00007.bin
│ │ ├── pytorch_model-00006-of-00007.bin
│ │ ├── pytorch_model-00007-of-00007.bin
│ │ ├── pytorch_model.bin.index.json
│ │ ├── special_tokens_map.json
│ │ ├── tokenizer_config.json
│ │ └── tokenizer.model
In the "Model" tab of the UI, those models can be automatically downloaded from Hugging Face. You can also download them via the command-line with python download-model.py organization/model.
- GGML models are a single file and should be placed directly into
models. Example:
text-generation-webui
├── models
│ ├── llama-13b.ggmlv3.q4_K_M.bin
Those models must be downloaded manually, as they are not currently supported by the automated downloader.
Instructions
GPT-4chan has been shut down from Hugging Face, so you need to download it elsewhere. You have two options:
The 32-bit version is only relevant if you intend to run the model in CPU mode. Otherwise, you should use the 16-bit version.
After downloading the model, follow these steps:
- Place the files under
models/gpt4chan_model_float16ormodels/gpt4chan_model. - Place GPT-J 6B's config.json file in that same folder: config.json.
- Download GPT-J 6B's tokenizer files (they will be automatically detected when you attempt to load GPT-4chan):
python download-model.py EleutherAI/gpt-j-6B --text-only
When you load this model in default or notebook modes, the "HTML" tab will show the generated text in 4chan format:
conda activate textgen
cd text-generation-webui
python server.py
Then browse to
http://localhost:7860/?__theme=dark
Optionally, you can use the following command-line flags:
| Flag | Description |
|---|---|
-h, --help |
Show this help message and exit. |
--multi-user |
Multi-user mode. Chat histories are not saved or automatically loaded. WARNING: this is highly experimental. |
--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. |
| Flag | Description |
|---|---|
--loader LOADER |
Choose the model loader manually, otherwise, it will get autodetected. Valid options: transformers, autogptq, gptq-for-llama, exllama, exllama_hf, llamacpp, rwkv, ctransformers |
| Flag | Description |
|---|---|
--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. |
--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. |
--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-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). |
--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. |
--xformers |
Use xformer's memory efficient attention. This should increase your tokens/s. |
--sdp-attention |
Use torch 2.0's sdp attention. |
--trust-remote-code |
Set trust_remote_code=True while loading a model. Necessary for ChatGLM and Falcon. |
| Flag | Description |
|---|---|
--load-in-4bit |
Load the model with 4-bit precision (using bitsandbytes). |
--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. |
--use_double_quant |
use_double_quant for 4-bit. |
| Flag | Description |
|---|---|
--threads |
Number of threads to use. |
--n_batch |
Maximum number of prompt tokens to batch together when calling llama_eval. |
--n-gpu-layers N_GPU_LAYERS |
Number of layers to offload to the GPU. Only works if llama-cpp-python was compiled with BLAS. Set this to 1000000000 to offload all layers to the GPU. |
--n_ctx N_CTX |
Size of the prompt context. |
| Flag | Description |
|---|---|
--no-mmap |
Prevent mmap from being used. |
--mlock |
Force the system to keep the model in RAM. |
--mul_mat_q |
Activate new mulmat kernels. |
--cache-capacity CACHE_CAPACITY |
Maximum cache capacity. Examples: 2000MiB, 2GiB. When provided without units, bytes will be assumed. |
--tensor_split TENSOR_SPLIT |
Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17 |
--llama_cpp_seed SEED |
Seed for llama-cpp models. Default 0 (random). |
--n_gqa N_GQA |
grouped-query attention. Must be 8 for llama-2 70b. |
--rms_norm_eps RMS_NORM_EPS |
5e-6 is a good value for llama-2 models. |
--cpu |
Use the CPU version of llama-cpp-python instead of the GPU-accelerated version. |
| Flag | Description |
|---|---|
--model_type MODEL_TYPE |
Model type of pre-quantized model. Currently gpt2, gptj, gptneox, falcon, llama, mpt, starcoder (gptbigcode), dollyv2, and replit are supported. |
| Flag | Description |
|---|---|
--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 don't 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. |
| Flag | Description |
|---|---|
--gpu-split |
Comma-separated list of VRAM (in GB) to use per GPU device for model layers, e.g. 20,7,7 |
--max_seq_len MAX_SEQ_LEN |
Maximum sequence length. |
| Flag | Description |
|---|---|
--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. |
| 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. |
| Flag | Description |
|---|---|
--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. |
| Flag | Description |
|---|---|
--alpha_value ALPHA_VALUE |
Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both. |
--compress_pos_emb COMPRESS_POS_EMB |
Positional embeddings compression factor. Should typically be set to max_seq_len / 2048. |
| Flag | Description |
|---|---|
--listen |
Make the web UI reachable from your local network. |
--listen-host LISTEN_HOST |
The hostname 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. |
--auto-launch |
Open the web UI in the default browser upon launch. |
--gradio-auth USER:PWD |
set gradio authentication like "username:password"; or comma-delimit multiple like "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 this format: "u1:p1,u2:p2,u3:p3" |
--ssl-keyfile SSL_KEYFILE |
The path to the SSL certificate key file. |
--ssl-certfile SSL_CERTFILE |
The path to the SSL certificate cert file. |
| 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-blocking-port BLOCKING_PORT |
The listening port for the blocking API. |
--api-streaming-port STREAMING_PORT |
The listening port for the streaming API. |
| Flag | Description |
|---|---|
--multimodal-pipeline PIPELINE |
The multimodal pipeline to use. Examples: llava-7b, llava-13b. |
Inference settings presets can be created under presets/ as yaml files. These files are detected automatically at startup.