Update README.md
Browse files
README.md
CHANGED
|
@@ -6,14 +6,40 @@ tags:
|
|
| 6 |
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- grpo
|
|
|
|
|
|
|
| 9 |
licence: license
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
-
# Model Card for
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
|
| 15 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
## Quick start
|
| 18 |
|
| 19 |
```python
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
- trl
|
| 8 |
- grpo
|
| 9 |
+
- deepseek
|
| 10 |
+
- r1
|
| 11 |
licence: license
|
| 12 |
+
license: apache-2.0
|
| 13 |
+
datasets:
|
| 14 |
+
- bhaviktheslider/JSON-Unstructured-Structured
|
| 15 |
---
|
| 16 |
|
| 17 |
+
# Model Card for MasterControlAIML/DeepSeek-R1-Qwen-2.5-1.5b
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
|
| 20 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 21 |
|
| 22 |
+
---
|
| 23 |
+
license: apache-2.0
|
| 24 |
+
|
| 25 |
+
Datasets:
|
| 26 |
+
- MasterControlAIML/JSON-Unstructured-Structured
|
| 27 |
+
|
| 28 |
+
---
|
| 29 |
+
|
| 30 |
+
# DeepSeek R1 Strategy Replication on Qwen-2.5-1.5b on 8*H100 GPUS
|
| 31 |
+
|
| 32 |
+
*Problem - Unstructured to Structured JSON Creation*
|
| 33 |
+
|
| 34 |
+
*Currently updating as model is still running*
|
| 35 |
+
|
| 36 |
+
*Desired Input - Unstructured Text Paragraphs and Blank Schema Rules*
|
| 37 |
+
|
| 38 |
+
*Output - Filled Created JSON from Unstructured Text following Blank Schema Rules*
|
| 39 |
+
|
| 40 |
+
*Dataset Link to Understand More - https://huggingface.co/datasets/MasterControlAIML/JSON-Unstructured-Structured*
|
| 41 |
+
|
| 42 |
+
|
| 43 |
## Quick start
|
| 44 |
|
| 45 |
```python
|