diff --git a/docs/LLaMA-model.md b/docs/LLaMA-model.md index 6706b16d..36e9c305 100644 --- a/docs/LLaMA-model.md +++ b/docs/LLaMA-model.md @@ -28,17 +28,15 @@ Once downloaded, it will be automatically applied to **every** `LlamaForCausalLM pip install protobuf==3.20.1 ``` -2. Use the script below to convert the model in `.pth` format that you, a fellow academic, downloaded using Meta's official link: +2. Use the script below to convert the model in `.pth` format that you, a fellow academic, downloaded using Meta's official link. -### Convert LLaMA to HuggingFace format - -If you have `transformers` installed in place +If you have `transformers` installed in place: ``` python -m transformers.models.llama.convert_llama_weights_to_hf --input_dir /path/to/LLaMA --model_size 7B --output_dir /tmp/outputs/llama-7b ``` -Otherwise download script [convert_llama_weights_to_hf.py](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py) +Otherwise download [convert_llama_weights_to_hf.py](https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/convert_llama_weights_to_hf.py) first and run: ``` python convert_llama_weights_to_hf.py --input_dir /path/to/LLaMA --model_size 7B --output_dir /tmp/outputs/llama-7b diff --git a/extensions/api/blocking_api.py b/extensions/api/blocking_api.py index c787cd0f..0d228880 100644 --- a/extensions/api/blocking_api.py +++ b/extensions/api/blocking_api.py @@ -5,12 +5,14 @@ from threading import Thread from extensions.api.util import build_parameters, try_start_cloudflared from modules import shared from modules.chat import generate_chat_reply -from modules.text_generation import encode, generate_reply, stop_everything_event -from modules.models import load_model, unload_model from modules.LoRA import add_lora_to_model +from modules.models import load_model, unload_model +from modules.text_generation import (encode, generate_reply, + stop_everything_event) from modules.utils import get_available_models from server import get_model_specific_settings, update_model_parameters + def get_model_info(): return { 'model_name': shared.model_name,