Commit
•
358b059
1
Parent(s):
e32a14f
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,26 @@ license_name: yi-license
|
|
| 4 |
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
|
| 5 |
---
|
| 6 |
|
| 7 |
-
This is a 6.0bpw quantized version of [DrNicefellow/ChatAllInOne-Yi-34B-200K-V1](https://huggingface.co/DrNicefellow/ChatAllInOne-Yi-34B-200K-V1) made with [exllamav2](https://github.com/turboderp/exllamav2).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
|
| 5 |
---
|
| 6 |
|
| 7 |
+
This is a 6.0bpw quantized version of [DrNicefellow/ChatAllInOne-Yi-34B-200K-V1](https://huggingface.co/DrNicefellow/ChatAllInOne-Yi-34B-200K-V1) made with [exllamav2](https://github.com/turboderp/exllamav2).
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
## Model Details
|
| 11 |
+
- **Base Model**: [01-ai/Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K)
|
| 12 |
+
- **Fine-tuning Technique**: QLoRA (Quantum Logic-based Reasoning Approach)
|
| 13 |
+
- **Dataset**: [CHAT-ALL-IN-ONE-v1](https://huggingface.co/datasets/DrNicefellow/CHAT-ALL-IN-ONE-v1)
|
| 14 |
+
- **Tool Used for Fine-tuning**: [unsloth](https://github.com/unslothai/unsloth)
|
| 15 |
+
|
| 16 |
+
## Features
|
| 17 |
+
- Enhanced understanding and generation of conversational language.
|
| 18 |
+
- Improved performance in diverse chat scenarios, including casual, formal, and domain-specific conversations.
|
| 19 |
+
- Fine-tuned to maintain context and coherence over longer dialogues.
|
| 20 |
+
|
| 21 |
+
## Prompt Format
|
| 22 |
+
|
| 23 |
+
Vicuna 1.1
|
| 24 |
+
|
| 25 |
+
See the finetuning dataset for examples.
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
## License
|
| 29 |
+
This model is open-sourced under the [Yi License](https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE).
|