初始化项目,由ModelHub XC社区提供模型
Model: Neelectric/Llama-3.1-8B-Instruct_SFT_mathfisher_v00.05 Source: Original Platform
This commit is contained in:
60
README.md
Normal file
60
README.md
Normal file
@@ -0,0 +1,60 @@
|
||||
---
|
||||
base_model: meta-llama/Llama-3.1-8B-Instruct
|
||||
datasets: Neelectric/OpenR1-Math-220k_all_Llama3_4096toks
|
||||
library_name: transformers
|
||||
model_name: Llama-3.1-8B-Instruct_SFT_mathfisher_v00.05
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- sft
|
||||
- trl
|
||||
- open-r1
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for Llama-3.1-8B-Instruct_SFT_mathfisher_v00.05
|
||||
|
||||
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the [Neelectric/OpenR1-Math-220k_all_Llama3_4096toks](https://huggingface.co/datasets/Neelectric/OpenR1-Math-220k_all_Llama3_4096toks) dataset.
|
||||
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="Neelectric/Llama-3.1-8B-Instruct_SFT_mathfisher_v00.05", 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/neelectric/open-r1_math/runs/4krdbtj9)
|
||||
|
||||
|
||||
|
||||
This model was trained with SFT.
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 1.1.0.dev0
|
||||
- Transformers: 4.57.6
|
||||
- Pytorch: 2.9.0
|
||||
- Datasets: 4.8.5
|
||||
- Tokenizers: 0.22.2
|
||||
|
||||
## Citations
|
||||
|
||||
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@software{vonwerra2020trl,
|
||||
title = {{TRL: Transformers Reinforcement Learning}},
|
||||
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
||||
license = {Apache-2.0},
|
||||
url = {https://github.com/huggingface/trl},
|
||||
year = {2020}
|
||||
}
|
||||
```
|
||||
Reference in New Issue
Block a user