Instructions to use UCSC-VLAA/MedReason-Mistral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UCSC-VLAA/MedReason-Mistral with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="UCSC-VLAA/MedReason-Mistral")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("UCSC-VLAA/MedReason-Mistral", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from UCSC-VLAA/MedReason-Mistral: direct link, hf CLI and curl.
- Browser
- Download file 3.51 MB
-
https://huggingface.co/UCSC-VLAA/MedReason-Mistral/resolve/refs%2Fpr%2F1/tokenizer.json
- Command line
-
hf download hf://UCSC-VLAA/MedReason-Mistral@refs/pr/1/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/UCSC-VLAA/MedReason-Mistral/resolve/refs%2Fpr%2F1/tokenizer.json
3.51 MB
- Xet hash:
- f56b4429655c277aadaff70a90a7c681b97617f30f816a0f26424e9787f455ab
- Size of remote file:
- 3.51 MB
- SHA256:
- 835cf54bb933752267652500a9243a9002107bbb4501b99f8d2f46ccfdad2567
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.