Instructions to use RajuEEE/Generative_Question_Answering_LLama2_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use RajuEEE/Generative_Question_Answering_LLama2_v2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("abhishek/llama-2-7b-hf-small-shards") model = PeftModel.from_pretrained(base_model, "RajuEEE/Generative_Question_Answering_LLama2_v2") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from RajuEEE/Generative_Question_Answering_LLama2_v2: direct link, hf CLI and curl.
- Browser
- Download file 33.6 MB
-
https://huggingface.co/RajuEEE/Generative_Question_Answering_LLama2_v2/resolve/main/adapter_model.bin
- Command line
-
hf download hf://RajuEEE/Generative_Question_Answering_LLama2_v2/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/RajuEEE/Generative_Question_Answering_LLama2_v2/resolve/main/adapter_model.bin
33.6 MB
- Xet hash:
- f31bbe491e762fb77d6f3c72ad36bd883d23e2bd1ad2f2b4f66fefffba200ae2
- Size of remote file:
- 33.6 MB
- SHA256:
- 4774bac42e0d98af211b20c78f2ec2454cad8262f5b97210d5d14972106d28dc
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.