Model save
Browse files- README.md +2 -2
- generation_config.json +14 -0
README.md
CHANGED
@@ -35,10 +35,10 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
|
|
35 |
### Framework versions
|
36 |
|
37 |
- TRL: 0.14.0
|
38 |
-
- Transformers: 4.
|
39 |
- Pytorch: 2.1.0+cu118
|
40 |
- Datasets: 3.2.0
|
41 |
-
- Tokenizers: 0.21.
|
42 |
|
43 |
## Citations
|
44 |
|
|
|
35 |
### Framework versions
|
36 |
|
37 |
- TRL: 0.14.0
|
38 |
+
- Transformers: 4.47.1
|
39 |
- Pytorch: 2.1.0+cu118
|
40 |
- Datasets: 3.2.0
|
41 |
+
- Tokenizers: 0.21.1
|
42 |
|
43 |
## Citations
|
44 |
|
generation_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 151643,
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": [
|
5 |
+
151645,
|
6 |
+
151643
|
7 |
+
],
|
8 |
+
"pad_token_id": 151643,
|
9 |
+
"repetition_penalty": 1.1,
|
10 |
+
"temperature": 0.7,
|
11 |
+
"top_k": 20,
|
12 |
+
"top_p": 0.8,
|
13 |
+
"transformers_version": "4.47.1"
|
14 |
+
}
|