Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,23 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
datasets:
|
| 4 |
+
- teknium/OpenHermes-2.5
|
| 5 |
+
- m-a-p/CodeFeedback-Filtered-Instruction
|
| 6 |
+
- m-a-p/Code-Feedback
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
---
|
| 9 |
+
# Wukong-0.1-Mistral-7B-v0.2
|
| 10 |
+
|
| 11 |
+
Join Our Discord! https://discord.gg/cognitivecomputations
|
| 12 |
+
|
| 13 |
+
Wukong-0.1-Mistral-7B-v0.2 is a dealigned chat finetune of the original fantastic Mistral-7B-v0.2 model by the Mistral team.
|
| 14 |
+
|
| 15 |
+
This model was trained on the teknium OpenHeremes-2.5 dataset, code datasets from Multimodal Art Projection https://m-a-p.ai Cognitive Computations https://erichartford.com/dolphin 🐬
|
| 16 |
+
|
| 17 |
+
This model was trained for 3 epochs over 4 4090's.
|
| 18 |
+
|
| 19 |
+
# Example Outputs
|
| 20 |
+
|
| 21 |
+
TBD
|
| 22 |
+
|
| 23 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|