Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,7 @@ library_name: transformers
|
|
| 16 |
**Model Description:**
|
| 17 |
|
| 18 |
GRPO-VI-Qwen2-7B-RAG is a large language model fine-tuned from the base model Qwen2.5-7B-Instruct (https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) to serve Retrieval-Augmented Generation (RAG) tasks. The fine-tuning process involves Supervised Fine-Tuning combined with GRPO (Group Relative Policy Optimization).
|
|
|
|
| 19 |
The model is trained on a Vietnamese-language dataset with the goal of improving Vietnamese language understanding and generation capabilities, while enhancing performance on tasks that require integrating information retrieved from external documents.
|
| 20 |
|
| 21 |
**Purpose of Use:**
|
|
|
|
| 16 |
**Model Description:**
|
| 17 |
|
| 18 |
GRPO-VI-Qwen2-7B-RAG is a large language model fine-tuned from the base model Qwen2.5-7B-Instruct (https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) to serve Retrieval-Augmented Generation (RAG) tasks. The fine-tuning process involves Supervised Fine-Tuning combined with GRPO (Group Relative Policy Optimization).
|
| 19 |
+
|
| 20 |
The model is trained on a Vietnamese-language dataset with the goal of improving Vietnamese language understanding and generation capabilities, while enhancing performance on tasks that require integrating information retrieved from external documents.
|
| 21 |
|
| 22 |
**Purpose of Use:**
|