Instructions to use wasertech/assistant-llama2-7b-chat-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use wasertech/assistant-llama2-7b-chat-qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Photolens/llama-2-7b-langchain-chat") model = PeftModel.from_pretrained(base_model, "wasertech/assistant-llama2-7b-chat-qlora") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from wasertech/assistant-llama2-7b-chat-qlora: direct link, hf CLI and curl.
- Browser
- Download file 134 MB
-
https://huggingface.co/wasertech/assistant-llama2-7b-chat-qlora/resolve/main/adapter_model.bin
- Command line
-
hf download hf://wasertech/assistant-llama2-7b-chat-qlora/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/wasertech/assistant-llama2-7b-chat-qlora/resolve/main/adapter_model.bin
134 MB
- Xet hash:
- 49e9dccb20590a37201114b9c66b6f28499d56d0bb18b7ffed5cf651f6f4c3c7
- Size of remote file:
- 134 MB
- SHA256:
- 3eaf04d8c2e37f8243f654dd9d14832c865aa620d81490c4006b90e1ce087d98
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.