DrNicefellow
commited on
Commit
•
d3fb17c
1
Parent(s):
6ee5391
Update README.md
Browse files
README.md
CHANGED
@@ -1,22 +1,30 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
-
|
4 |
-
|
5 |
-
tags:
|
6 |
-
- text-generation-inference
|
7 |
-
- transformers
|
8 |
-
- unsloth
|
9 |
-
- llama
|
10 |
-
- trl
|
11 |
-
base_model: 01-ai/Yi-34B-200K
|
12 |
---
|
|
|
13 |
|
14 |
-
|
|
|
15 |
|
16 |
-
|
17 |
-
- **
|
18 |
-
- **
|
|
|
|
|
19 |
|
20 |
-
|
|
|
|
|
|
|
21 |
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: other
|
3 |
+
license_name: yi-license
|
4 |
+
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
---
|
6 |
+
# ChatAllInOne-Yi-34B-200K-V1
|
7 |
|
8 |
+
## Description
|
9 |
+
ChatAllInOne-Yi-34B-200K-V1 is a chat language model fine-tuned on the CHAT-ALL-IN-ONE-v1 dataset using the QLoRA technique with the unsloth tool. Originally based on the 01-ai/Yi-34B-200K model, this version is specifically optimized for diverse and comprehensive chat applications.
|
10 |
|
11 |
+
## Model Details
|
12 |
+
- **Base Model**: [01-ai/Yi-34B-200K](https://huggingface.co/01-ai/Yi-34B-200K)
|
13 |
+
- **Fine-tuning Technique**: QLoRA (Quantum Logic-based Reasoning Approach)
|
14 |
+
- **Dataset**: [CHAT-ALL-IN-ONE-v1](https://huggingface.co/datasets/DrNicefellow/CHAT-ALL-IN-ONE-v1)
|
15 |
+
- **Tool Used for Fine-tuning**: [unsloth](https://github.com/unslothai/unsloth)
|
16 |
|
17 |
+
## Features
|
18 |
+
- Enhanced understanding and generation of conversational language.
|
19 |
+
- Improved performance in diverse chat scenarios, including casual, formal, and domain-specific conversations.
|
20 |
+
- Fine-tuned to maintain context and coherence over longer dialogues.
|
21 |
|
22 |
+
## Prompt Format
|
23 |
+
|
24 |
+
Vicuna 1.1
|
25 |
+
|
26 |
+
See the finetuning dataset for examples.
|
27 |
+
|
28 |
+
|
29 |
+
## License
|
30 |
+
This model is open-sourced under the [Yi License](https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE).
|