From 406995f7224073a7bfbee6a2ce4e67f723a21e36 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Mon, 19 Aug 2024 21:24:01 -0700 Subject: [PATCH] Update README --- README.md | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index 230dfccf..0e264c75 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ Its goal is to become the [AUTOMATIC1111/stable-diffusion-webui](https://github. ## Features -* Multiple backends for text generation in a single UI and API, including [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), and [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM). +* Multiple backends for text generation in a single UI and API, including [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), and [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM). The Transformers loader also supports models quantized through [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) and [HQQ](https://github.com/mobiusml/hqq). * OpenAI-compatible API server with Chat and Completions endpoints – see the [examples](https://github.com/oobabooga/text-generation-webui/wiki/12-%E2%80%90-OpenAI-API#examples). * Automatic prompt formatting for each model using the Jinja2 template in its metadata, ensuring high-quality outputs without manual intervention. * Three chat modes: `instruct`, `chat-instruct`, and `chat`, allowing for both task-based interactions and casual conversations with characters. `chat-instruct` mode automatically applies the model's template to the chat's prompt, leading to higher quality outputs. @@ -209,13 +209,13 @@ usage: server.py [-h] [--multi-user] [--character CHARACTER] [--model MODEL] [-- [--force-safetensors] [--no_use_fast] [--use_flash_attention_2] [--use_eager_attention] [--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] [--no_xformers] [--no_sdpa] - [--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] [--cpp-runner] [--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] [--subpath SUBPATH] [--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] + [--attention-sink-size ATTENTION_SINK_SIZE] [--tokenizer-dir TOKENIZER_DIR] [--gpu-split GPU_SPLIT] [--autosplit] [--max_seq_len MAX_SEQ_LEN] [--cfg-cache] [--no_flash_attn] + [--no_xformers] [--no_sdpa] [--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] [--hqq-backend HQQ_BACKEND] [--cpp-runner] [--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] + [--subpath SUBPATH] [--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] [--no_inject_fused_attention] Text generation web UI @@ -239,7 +239,7 @@ Basic settings: 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. + AutoGPTQ. Transformers/Accelerate: --cpu Use the CPU to generate text. Warning: Training on CPU is extremely slow. @@ -283,6 +283,7 @@ llama.cpp: --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. + --tokenizer-dir TOKENIZER_DIR Load the tokenizer from this folder. Meant to be used with llamacpp_HF through the command-line. ExLlamaV2: --gpu-split GPU_SPLIT Comma-separated list of VRAM (in GB) to use per GPU device for model layers. Example: 20,7,7. @@ -306,9 +307,6 @@ AutoGPTQ: --wbits WBITS Load a pre-quantized model with specified precision in bits. 2, 3, 4 and 8 are supported. --groupsize GROUPSIZE Group size. -AutoAWQ: - --no_inject_fused_attention Disable the use of fused attention, which will use less VRAM at the cost of slower inference. - HQQ: --hqq-backend HQQ_BACKEND Backend for the HQQ loader. Valid options: PYTORCH, PYTORCH_COMPILE, ATEN.