|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- teknium/OpenHermes-2.5 |
|
- m-a-p/CodeFeedback-Filtered-Instruction |
|
- m-a-p/Code-Feedback |
|
pipeline_tag: text-generation |
|
--- |
|
# Wukong-0.1-Mistral-7B-v0.2 |
|
|
|
Join Our Discord! https://discord.gg/cognitivecomputations |
|
|
|
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/655dc641accde1bbc8b41aec/xOe1Nb3S9Nb53us7_Ja3s.jpeg) |
|
|
|
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. |
|
|
|
This model was trained on the teknium OpenHeremes-2.5 dataset, code datasets from Multimodal Art Projection https://m-a-p.ai, and the Dolphin dataset from Cognitive Computations https://erichartford.com/dolphin 🐬 |
|
|
|
This model was trained for 3 epochs over 4 4090's. |
|
|
|
# Example Outputs |
|
|
|
TBD |
|
|
|
[<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) |