Update README.md
Browse files
README.md
CHANGED
@@ -27,14 +27,14 @@ pipeline_tag: text-generation
|
|
27 |
|
28 |
## **Model Overview**
|
29 |
|
30 |
-
This model is a fine-tuned version of
|
31 |
|
32 |
Fine-tuning was performed using **Hugging Face’s TRL (Transformers Reinforcement Learning) library**, ensuring adaptability for **complex reasoning, natural language generation (NLG), and conversational AI** tasks.
|
33 |
|
34 |
## **Model Details**
|
35 |
|
36 |
- **Developed by:** Daemontatox
|
37 |
-
- **Base Model:**
|
38 |
- **License:** Apache-2.0
|
39 |
- **Model Type:** Qwen2-based large-scale transformer
|
40 |
- **Optimization Framework:** [Unsloth](https://github.com/unslothai/unsloth)
|
|
|
27 |
|
28 |
## **Model Overview**
|
29 |
|
30 |
+
This model is a fine-tuned version of**unsloth/QwQ-32B-Preview**, based on the **Qwen2.5** architecture. It has been optimized using **Unsloth** for significantly improved training efficiency, reducing compute time by **2x** while maintaining high performance across various NLP benchmarks.
|
31 |
|
32 |
Fine-tuning was performed using **Hugging Face’s TRL (Transformers Reinforcement Learning) library**, ensuring adaptability for **complex reasoning, natural language generation (NLG), and conversational AI** tasks.
|
33 |
|
34 |
## **Model Details**
|
35 |
|
36 |
- **Developed by:** Daemontatox
|
37 |
+
- **Base Model:** unsloth/QwQ-32B-Preview
|
38 |
- **License:** Apache-2.0
|
39 |
- **Model Type:** Qwen2-based large-scale transformer
|
40 |
- **Optimization Framework:** [Unsloth](https://github.com/unslothai/unsloth)
|