End of training
Browse files- README.md +3 -1
- config.json +1 -1
README.md
CHANGED
|
@@ -1,9 +1,11 @@
|
|
| 1 |
---
|
| 2 |
base_model: HuggingFaceTB/SmolLM3-3B
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
model_name: DeepSeek-R1-Distill-SmolLM3-3B-GRPO
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- trl
|
| 8 |
- sft
|
| 9 |
licence: license
|
|
@@ -11,7 +13,7 @@ licence: license
|
|
| 11 |
|
| 12 |
# Model Card for DeepSeek-R1-Distill-SmolLM3-3B-GRPO
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
## Quick start
|
|
|
|
| 1 |
---
|
| 2 |
base_model: HuggingFaceTB/SmolLM3-3B
|
| 3 |
+
datasets: open-r1/OpenR1-Math-220k
|
| 4 |
library_name: transformers
|
| 5 |
model_name: DeepSeek-R1-Distill-SmolLM3-3B-GRPO
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
+
- open-r1
|
| 9 |
- trl
|
| 10 |
- sft
|
| 11 |
licence: license
|
|
|
|
| 13 |
|
| 14 |
# Model Card for DeepSeek-R1-Distill-SmolLM3-3B-GRPO
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [HuggingFaceTB/SmolLM3-3B](https://huggingface.co/HuggingFaceTB/SmolLM3-3B) on the [open-r1/OpenR1-Math-220k](https://huggingface.co/datasets/open-r1/OpenR1-Math-220k) dataset.
|
| 17 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 18 |
|
| 19 |
## Quick start
|
config.json
CHANGED
|
@@ -102,7 +102,7 @@
|
|
| 102 |
"sliding_window": null,
|
| 103 |
"torch_dtype": "float16",
|
| 104 |
"transformers_version": "4.55.0",
|
| 105 |
-
"use_cache":
|
| 106 |
"use_sliding_window": false,
|
| 107 |
"vocab_size": 128256
|
| 108 |
}
|
|
|
|
| 102 |
"sliding_window": null,
|
| 103 |
"torch_dtype": "float16",
|
| 104 |
"transformers_version": "4.55.0",
|
| 105 |
+
"use_cache": true,
|
| 106 |
"use_sliding_window": false,
|
| 107 |
"vocab_size": 128256
|
| 108 |
}
|