初始化项目,由ModelHub XC社区提供模型

Model: hZzy/mistral-7b-sft-7b-submission-full
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-31 20:21:49 +08:00
commit 28f60b7925
18 changed files with 284222 additions and 0 deletions

58
README.md Normal file
View File

@@ -0,0 +1,58 @@
---
base_model: mistralai/Mistral-7B-Instruct-v0.3
library_name: transformers
model_name: mistral-7b-sft-7b-submission-full
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for mistral-7b-sft-7b-submission-full
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="hZzy/mistral-7b-sft-7b-submission-full", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/zhiyuzha-university-of-florida/huggingface/runs/csg33j3u)
This model was trained with SFT.
### Framework versions
- TRL: 0.20.0
- Transformers: 4.54.1
- Pytorch: 2.7.0+cu128
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```