Update README.md
Browse files
README.md
CHANGED
@@ -1,58 +1,24 @@
|
|
1 |
-
|
2 |
-
base_model: Qwen/Qwen2.5-32B-Instruct
|
3 |
-
library_name: transformers
|
4 |
-
model_name: Qwen2.5-32B-Instruct-20250119_201826
|
5 |
-
tags:
|
6 |
-
- generated_from_trainer
|
7 |
-
- trl
|
8 |
-
- sft
|
9 |
-
licence: license
|
10 |
-
---
|
11 |
|
12 |
-
|
|
|
13 |
|
14 |
-
|
15 |
-
It has been trained using [TRL](https://github.com/huggingface/trl).
|
16 |
|
17 |
-
|
18 |
|
19 |
-
|
20 |
-
from transformers import pipeline
|
21 |
-
|
22 |
-
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?"
|
23 |
-
generator = pipeline("text-generation", model="qfq/Qwen2.5-32B-Instruct-20250119_201826", device="cuda")
|
24 |
-
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
25 |
-
print(output["generated_text"])
|
26 |
-
```
|
27 |
-
|
28 |
-
## Training procedure
|
29 |
|
30 |
[<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/hashimoto-group/o1/runs/xaantfal)
|
31 |
|
32 |
-
|
33 |
-
This model was trained with SFT.
|
34 |
-
|
35 |
-
### Framework versions
|
36 |
-
|
37 |
- TRL: 0.13.0
|
38 |
- Transformers: 4.48.0
|
39 |
- Pytorch: 2.3.1
|
40 |
- Datasets: 3.0.1
|
41 |
- Tokenizers: 0.21.0
|
42 |
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
|
47 |
-
Cite TRL as:
|
48 |
-
|
49 |
```bibtex
|
50 |
-
|
51 |
-
title = {{TRL: Transformer Reinforcement Learning}},
|
52 |
-
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 Gallouédec},
|
53 |
-
year = 2020,
|
54 |
-
journal = {GitHub repository},
|
55 |
-
publisher = {GitHub},
|
56 |
-
howpublished = {\url{https://github.com/huggingface/trl}}
|
57 |
-
}
|
58 |
```
|
|
|
1 |
+
# Model Summary
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
3 |
+
- **Repository:** [simplescaling/s1](https://github.com/simplescaling/s1)
|
4 |
+
- **Paper:** TODO
|
5 |
|
6 |
+
# Use
|
|
|
7 |
|
8 |
+
This is the token-conditional control model for our paper. You can evaluate using the information [here](https://github.com/simplescaling/s1?tab=readme-ov-file#evaluation).
|
9 |
|
10 |
+
# Training information
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
[<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/hashimoto-group/o1/runs/xaantfal)
|
13 |
|
|
|
|
|
|
|
|
|
|
|
14 |
- TRL: 0.13.0
|
15 |
- Transformers: 4.48.0
|
16 |
- Pytorch: 2.3.1
|
17 |
- Datasets: 3.0.1
|
18 |
- Tokenizers: 0.21.0
|
19 |
|
20 |
+
# Citation
|
|
|
|
|
21 |
|
|
|
|
|
22 |
```bibtex
|
23 |
+
TODO
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
```
|