End of training
Browse files- README.md +7 -1
- config.json +1 -1
README.md
CHANGED
@@ -3,9 +3,15 @@ library_name: transformers
|
|
3 |
license: apache-2.0
|
4 |
base_model: Qwen/Qwen2-Math-1.5B-Instruct
|
5 |
tags:
|
|
|
6 |
- trl
|
7 |
- dpo
|
8 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: qwen2-math-1_5b-step-dpo
|
11 |
results: []
|
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# qwen2-math-1_5b-step-dpo
|
18 |
|
19 |
-
This model is a fine-tuned version of [Qwen/Qwen2-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-Math-1.5B-Instruct) on
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
3 |
license: apache-2.0
|
4 |
base_model: Qwen/Qwen2-Math-1.5B-Instruct
|
5 |
tags:
|
6 |
+
- alignment-handbook
|
7 |
- trl
|
8 |
- dpo
|
9 |
- generated_from_trainer
|
10 |
+
- trl
|
11 |
+
- dpo
|
12 |
+
- generated_from_trainer
|
13 |
+
datasets:
|
14 |
+
- xinlai/Math-Step-DPO-10K
|
15 |
model-index:
|
16 |
- name: qwen2-math-1_5b-step-dpo
|
17 |
results: []
|
|
|
22 |
|
23 |
# qwen2-math-1_5b-step-dpo
|
24 |
|
25 |
+
This model is a fine-tuned version of [Qwen/Qwen2-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-Math-1.5B-Instruct) on the xinlai/Math-Step-DPO-10K dataset.
|
26 |
|
27 |
## Model description
|
28 |
|
config.json
CHANGED
@@ -22,7 +22,7 @@
|
|
22 |
"tie_word_embeddings": true,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.44.2",
|
25 |
-
"use_cache":
|
26 |
"use_mrope": false,
|
27 |
"use_sliding_window": false,
|
28 |
"vocab_size": 151936
|
|
|
22 |
"tie_word_embeddings": true,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
"transformers_version": "4.44.2",
|
25 |
+
"use_cache": true,
|
26 |
"use_mrope": false,
|
27 |
"use_sliding_window": false,
|
28 |
"vocab_size": 151936
|