Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: other
|
|
| 3 |
license_name: qwen-research
|
| 4 |
license_link: >-
|
| 5 |
https://raw.githubusercontent.com/QwenLM/Qwen/refs/heads/main/Tongyi%20Qianwen%20RESEARCH%20LICENSE%20AGREEMENT
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# Chirp-3b
|
|
@@ -17,8 +19,6 @@ Chirp-3b is an open-source effort to push the limits of what small-scale LLMs ca
|
|
| 17 |
|
| 18 |
- **Parameters**: 3 billion
|
| 19 |
- **Training Data**: 50M tokens distilled from GPT-4o
|
| 20 |
-
- **Fine-Tuned From**: [Base model name TBD—update if applicable]
|
| 21 |
-
- **License**: [Specify license, e.g., MIT, Apache 2.0, etc.—update as needed]
|
| 22 |
|
| 23 |
## Benchmarks
|
| 24 |
|
|
|
|
| 3 |
license_name: qwen-research
|
| 4 |
license_link: >-
|
| 5 |
https://raw.githubusercontent.com/QwenLM/Qwen/refs/heads/main/Tongyi%20Qianwen%20RESEARCH%20LICENSE%20AGREEMENT
|
| 6 |
+
base_model:
|
| 7 |
+
- Qwen/Qwen2.5-3B-Instruct
|
| 8 |
---
|
| 9 |
|
| 10 |
# Chirp-3b
|
|
|
|
| 19 |
|
| 20 |
- **Parameters**: 3 billion
|
| 21 |
- **Training Data**: 50M tokens distilled from GPT-4o
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Benchmarks
|
| 24 |
|