Training in progress, epoch 1
Browse files- README.md +2 -11
- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -4,7 +4,7 @@ library_name: transformers
|
|
| 4 |
model_name: mql-finetune
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
-
|
| 8 |
- trl
|
| 9 |
licence: license
|
| 10 |
---
|
|
@@ -31,7 +31,7 @@ print(output["generated_text"])
|
|
| 31 |
|
| 32 |
|
| 33 |
|
| 34 |
-
This model was trained with
|
| 35 |
|
| 36 |
### Framework versions
|
| 37 |
|
|
@@ -43,16 +43,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
|
|
| 43 |
|
| 44 |
## Citations
|
| 45 |
|
| 46 |
-
Cite GRPO as:
|
| 47 |
|
| 48 |
-
```bibtex
|
| 49 |
-
@article{shao2024deepseekmath,
|
| 50 |
-
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
|
| 51 |
-
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
|
| 52 |
-
year = 2024,
|
| 53 |
-
eprint = {arXiv:2402.03300},
|
| 54 |
-
}
|
| 55 |
-
```
|
| 56 |
|
| 57 |
Cite TRL as:
|
| 58 |
|
|
|
|
| 4 |
model_name: mql-finetune
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
- sft
|
| 8 |
- trl
|
| 9 |
licence: license
|
| 10 |
---
|
|
|
|
| 31 |
|
| 32 |
|
| 33 |
|
| 34 |
+
This model was trained with SFT.
|
| 35 |
|
| 36 |
### Framework versions
|
| 37 |
|
|
|
|
| 43 |
|
| 44 |
## Citations
|
| 45 |
|
|
|
|
| 46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
Cite TRL as:
|
| 49 |
|
adapter_config.json
CHANGED
|
@@ -30,12 +30,12 @@
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
| 33 |
-
"gate_proj",
|
| 34 |
"o_proj",
|
| 35 |
-
"up_proj",
|
| 36 |
"down_proj",
|
| 37 |
-
"k_proj",
|
| 38 |
"v_proj",
|
|
|
|
|
|
|
|
|
|
| 39 |
"q_proj"
|
| 40 |
],
|
| 41 |
"target_parameters": null,
|
|
|
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
|
|
|
| 33 |
"o_proj",
|
|
|
|
| 34 |
"down_proj",
|
|
|
|
| 35 |
"v_proj",
|
| 36 |
+
"gate_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
"q_proj"
|
| 40 |
],
|
| 41 |
"target_parameters": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9517e917b2cf5d12b013f431f8eda9893d620fd61d908335df57774106e6101
|
| 3 |
+
size 66127776
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9aa382ae7bb50f31fa3d152a9426d770fc36b2d3eaf859bfef058ffaaff5ffd2
|
| 3 |
+
size 5713
|