Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
```python
|
| 2 |
import torch
|
| 3 |
import transformers
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: tongyi-qianwen
|
| 4 |
+
base_model: Qwen/Qwen2-72B
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- axolotl
|
| 8 |
+
datasets:
|
| 9 |
+
- cognitivecomputations/Dolphin-2.9
|
| 10 |
+
- teknium/OpenHermes-2.5
|
| 11 |
+
- m-a-p/CodeFeedback-Filtered-Instruction
|
| 12 |
+
- cognitivecomputations/dolphin-coder
|
| 13 |
+
- cognitivecomputations/samantha-data
|
| 14 |
+
- microsoft/orca-math-word-problems-200k
|
| 15 |
+
- Locutusque/function-calling-chatml
|
| 16 |
+
- internlm/Agent-FLAN
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# DolphinVision 72b 🐬
|
| 20 |
+
|
| 21 |
+
Curated and trained by Quan Nguyen (qnguyen3/stablequan), Eric Hartford, and Cognitive Computations
|
| 22 |
+
|
| 23 |
+
[](https://discord.gg/cognitivecomputations)
|
| 24 |
+
Discord: https://discord.gg/cognitivecomputations
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
|
| 29 |
+
|
| 30 |
+
Our appreciation for the sponsors of DolphinVision:
|
| 31 |
+
- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xH100 node used for training
|
| 32 |
+
- [TensorWave](https://tensorwave.com/) - provided 8x mi300x node used for evaluations and inference
|
| 33 |
+
|
| 34 |
+
DolphinVision is a multimodal model. It is uncensored, and capable to reason and comment regarding images that other popular models would object to.
|
| 35 |
+
|
| 36 |
+
|
| 37 |
```python
|
| 38 |
import torch
|
| 39 |
import transformers
|