Update README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,15 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 3 |
library_name: transformers
|
| 4 |
-
model_name:
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- grpo
|
| 9 |
licence: license
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# Model Card for qwen-2.5-7b-r1-countdown
|
|
@@ -40,6 +43,27 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
|
|
| 40 |
- Datasets: 3.1.0
|
| 41 |
- Tokenizers: 0.21.0
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
## Citations
|
| 44 |
|
| 45 |
Cite GRPO as:
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen2.5-1.5B-Instruct
|
| 3 |
library_name: transformers
|
| 4 |
+
model_name: null
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- grpo
|
| 9 |
licence: license
|
| 10 |
+
license: apache-2.0
|
| 11 |
+
datasets:
|
| 12 |
+
- MasterControlAIML/JSON-Unstructured-Structured-Text
|
| 13 |
---
|
| 14 |
|
| 15 |
# Model Card for qwen-2.5-7b-r1-countdown
|
|
|
|
| 43 |
- Datasets: 3.1.0
|
| 44 |
- Tokenizers: 0.21.0
|
| 45 |
|
| 46 |
+
---
|
| 47 |
+
license: apache-2.0
|
| 48 |
+
datasets:
|
| 49 |
+
- MasterControlAIML/JSON-Unstructured-Structured
|
| 50 |
+
---
|
| 51 |
+
**DeepSeek R1 Strategy Replication on Qwen-2.5-1.5b on 8*H100 GPUS**
|
| 52 |
+
|
| 53 |
+
*Problem - Unstructured to Structured JSON Creation*
|
| 54 |
+
|
| 55 |
+
*Currently updating as model is still running*
|
| 56 |
+
|
| 57 |
+
*Desired Input - Unstructured Text Paragraphs and Blank Schema Rules*
|
| 58 |
+
|
| 59 |
+
*Output - Filled Created JSON from Unstructured Text following Blank Schema Rules*
|
| 60 |
+
|
| 61 |
+
*Dataset Link to Understand More - https://huggingface.co/datasets/MasterControlAIML/JSON-Unstructured-Structured*
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
|
| 67 |
## Citations
|
| 68 |
|
| 69 |
Cite GRPO as:
|