PEFT
TensorBoard
Safetensors
gemma
alignment-handbook
trl
sft
Generated from Trainer
4-bit precision
bitsandbytes
Instructions to use llama-duo/gemma7b-summarize with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use llama-duo/gemma7b-summarize with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-7b") model = PeftModel.from_pretrained(base_model, "llama-duo/gemma7b-summarize") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from llama-duo/gemma7b-summarize: direct link, hf CLI and curl.
- Browser
- Download file 17.5 MB
-
https://huggingface.co/llama-duo/gemma7b-summarize/resolve/main/tokenizer.json
- Command line
-
hf download hf://llama-duo/gemma7b-summarize/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/llama-duo/gemma7b-summarize/resolve/main/tokenizer.json
17.5 MB
- Xet hash:
- ae64183201b7a29ee6f78778b05cd61dcbb65132ceeef721c7b4f465027ba30f
- Size of remote file:
- 17.5 MB
- SHA256:
- 322a5f52ab5cab196761ab397a022d6fa3a2e1418585e532bb6efb2fedd2ae94
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.