Instructions to use avemio-digital/lora_model_chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use avemio-digital/lora_model_chat with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/mistral-7b-bnb-4bit") model = PeftModel.from_pretrained(base_model, "avemio-digital/lora_model_chat") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.safetensors from avemio-digital/lora_model_chat: direct link, hf CLI and curl.
- Browser
- Download file 168 MB
-
https://huggingface.co/avemio-digital/lora_model_chat/resolve/main/adapter_model.safetensors
- Command line
-
hf download hf://avemio-digital/lora_model_chat/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/avemio-digital/lora_model_chat/resolve/main/adapter_model.safetensors
168 MB
- Xet hash:
- c316bdc86851d5996312dd8ba7b200697815dd0f35d397d68d8de028286077bc
- Size of remote file:
- 168 MB
- SHA256:
- 1cd37f4739b0586c81c4f48ca286d5ea56e43933542ec1b4c825b0eb662f6dc1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.