Instructions to use sociocom/MedPHINER-Llama-3.1-Swallow-8B-Instruct-v0.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use sociocom/MedPHINER-Llama-3.1-Swallow-8B-Instruct-v0.5 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/data/llmcache/tokyotech-llm/Llama-3.1-Swallow-8B-Instruct-v0.5/") model = PeftModel.from_pretrained(base_model, "sociocom/MedPHINER-Llama-3.1-Swallow-8B-Instruct-v0.5") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from sociocom/MedPHINER-Llama-3.1-Swallow-8B-Instruct-v0.5: direct link, hf CLI and curl.
- Browser
- Download file 17.2 MB
-
https://huggingface.co/sociocom/MedPHINER-Llama-3.1-Swallow-8B-Instruct-v0.5/resolve/main/tokenizer.json
- Command line
-
hf download hf://sociocom/MedPHINER-Llama-3.1-Swallow-8B-Instruct-v0.5/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/sociocom/MedPHINER-Llama-3.1-Swallow-8B-Instruct-v0.5/resolve/main/tokenizer.json
17.2 MB
- Xet hash:
- ba82e7f8d68026730f675b0d5b6dd2756db4c18801c74bc82efbbe319c833555
- Size of remote file:
- 17.2 MB
- SHA256:
- 268aef6511a866fd03104209ff6592ded093172c0cdaf8885ff9c97d62e32869
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.