Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
datasets:
|
6 |
+
- cognitivecomputations/Dolphin-2.9
|
7 |
+
- teknium/OpenHermes-2.5
|
8 |
+
- m-a-p/CodeFeedback-Filtered-Instruction
|
9 |
+
- cognitivecomputations/dolphin-coder
|
10 |
+
- cognitivecomputations/samantha-data
|
11 |
+
- HuggingFaceH4/ultrachat_200k
|
12 |
+
- microsoft/orca-math-word-problems-200k
|
13 |
+
- abacusai/SystemChat-1.1
|
14 |
+
- Locutusque/function-calling-chatml
|
15 |
+
- internlm/Agent-FLAN
|
16 |
+
---
|
17 |
+
|
18 |
+
# Dolphin 2.9 Llama 3 8b 🐬
|
19 |
+
|
20 |
+
Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations
|
21 |
+
|
22 |
+
Discord: https://discord.gg/8fbBeC7ZGx
|
23 |
+
|
24 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
|
25 |
+
|
26 |
+
Our appreciation for the sponsors of Dolphin 2.9:
|
27 |
+
- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xH100 node
|
28 |
+
|
29 |
+
This model is based on Llama-3-70b, and is governed by [META LLAMA 3 COMMUNITY LICENSE AGREEMENT](LICENSE)
|
30 |
+
|
31 |
+
The base model has 8k context, and the qLoRA fine-tuning was with 8k sequence length.
|
32 |
+
|
33 |
+
It took 2.5 days on 8x L40S provided by Crusoe Cloud
|
34 |
+
|
35 |
+
This model was trained FFT on all parameters, using ChatML prompt template format.
|
36 |
+
|
37 |
+
example:
|
38 |
+
|
39 |
+
```
|
40 |
+
<|im_start|>system
|
41 |
+
You are Dolphin, a helpful AI assistant.<|im_end|>
|
42 |
+
<|im_start|>user
|
43 |
+
{prompt}<|im_end|>
|
44 |
+
<|im_start|>assistant
|
45 |
+
|
46 |
+
```
|
47 |
+
|
48 |
+
Dolphin-2.9 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
|
49 |
+
|
50 |
+
Dolphin is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
|
51 |
+
|
52 |
+
Dolphin is licensed according to Meta's Llama license. I grant permission for any use, including commercial, that falls within accordance with Meta's Llama-3 license. Dolphin was trained on data generated from GPT4, among other models.
|
53 |
+
|
54 |
+
[<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)
|
55 |
+
|
56 |
+
## Quants
|
57 |
+
|