From 7ffb424c7b154593f7aa6696633bd7ab1e656863 Mon Sep 17 00:00:00 2001 From: oobabooga <112222186+oobabooga@users.noreply.github.com> Date: Thu, 5 Oct 2023 09:22:37 -0700 Subject: [PATCH] Add AutoAWQ to README --- README.md | 2 +- modules/models_settings.py | 4 +--- 2 files changed, 2 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index 85115a2..1c502a1 100644 --- a/README.md +++ b/README.md @@ -11,7 +11,7 @@ Its goal is to become the [AUTOMATIC1111/stable-diffusion-webui](https://github. ## Features * 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), [ExLlama](https://github.com/turboderp/exllama), [ExLlamaV2](https://github.com/turboderp/exllamav2), [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ), [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa), [CTransformers](https://github.com/marella/ctransformers) +* Multiple model backends: [transformers](https://github.com/huggingface/transformers), [llama.cpp](https://github.com/ggerganov/llama.cpp), [ExLlama](https://github.com/turboderp/exllama), [ExLlamaV2](https://github.com/turboderp/exllamav2), [AutoGPTQ](https://github.com/PanQiWei/AutoGPTQ), [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa), [CTransformers](https://github.com/marella/ctransformers), [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) * 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 diff --git a/modules/models_settings.py b/modules/models_settings.py index 3f16876..aecb7a8 100644 --- a/modules/models_settings.py +++ b/modules/models_settings.py @@ -107,14 +107,12 @@ def infer_loader(model_name, model_settings): loader = None elif (path_to_model / 'quantize_config.json').exists() or ('wbits' in model_settings and type(model_settings['wbits']) is int and model_settings['wbits'] > 0): loader = 'AutoGPTQ' - elif (path_to_model / 'quant_config.json').exists(): + elif (path_to_model / 'quant_config.json').exists() or re.match(r'.*-awq', model_name.lower()): loader = 'AutoAWQ' elif len(list(path_to_model.glob('*.gguf'))) > 0: loader = 'llama.cpp' elif re.match(r'.*\.gguf', model_name.lower()): loader = 'llama.cpp' - elif re.match(r'.*-awq', model_name.lower()): - loader = 'AutoAWQ' elif re.match(r'.*rwkv.*\.pth', model_name.lower()): loader = 'RWKV' elif re.match(r'.*exl2', model_name.lower()):