End of training
Browse files- README.md +3 -1
- config.json +2 -1
README.md
CHANGED
@@ -1,8 +1,10 @@
|
|
1 |
---
|
|
|
2 |
library_name: transformers
|
3 |
model_name: Qwen2.5-1.5B-Open-R1-GRPO
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
- trl
|
7 |
- grpo
|
8 |
licence: license
|
@@ -10,7 +12,7 @@ licence: license
|
|
10 |
|
11 |
# Model Card for Qwen2.5-1.5B-Open-R1-GRPO
|
12 |
|
13 |
-
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
14 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
15 |
|
16 |
## Quick start
|
|
|
1 |
---
|
2 |
+
datasets: AI-MO/NuminaMath-TIR
|
3 |
library_name: transformers
|
4 |
model_name: Qwen2.5-1.5B-Open-R1-GRPO
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
+
- open-r1
|
8 |
- trl
|
9 |
- grpo
|
10 |
licence: license
|
|
|
12 |
|
13 |
# Model Card for Qwen2.5-1.5B-Open-R1-GRPO
|
14 |
|
15 |
+
This model is a fine-tuned version of [None](https://huggingface.co/None) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) dataset.
|
16 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
17 |
|
18 |
## Quick start
|
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"_name_or_path": "/home/zhaoyang/LLM_Weight/Qwen2-0.5B-Instruct",
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
@@ -22,7 +23,7 @@
|
|
22 |
"sliding_window": 32768,
|
23 |
"tie_word_embeddings": true,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
-
"transformers_version": "4.49.0
|
26 |
"use_cache": true,
|
27 |
"use_sliding_window": false,
|
28 |
"vocab_size": 151936
|
|
|
1 |
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
"_name_or_path": "/home/zhaoyang/LLM_Weight/Qwen2-0.5B-Instruct",
|
4 |
"architectures": [
|
5 |
"Qwen2ForCausalLM"
|
|
|
23 |
"sliding_window": 32768,
|
24 |
"tie_word_embeddings": true,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.49.0",
|
27 |
"use_cache": true,
|
28 |
"use_sliding_window": false,
|
29 |
"vocab_size": 151936
|