Update README.md
Browse files
README.md
CHANGED
|
@@ -1,11 +1,61 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-Nemo-Base-2407
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
- axolotl
|
| 7 |
+
datasets:
|
| 8 |
+
- cognitivecomputations/Dolphin-2.9
|
| 9 |
+
- teknium/OpenHermes-2.5
|
| 10 |
+
- m-a-p/CodeFeedback-Filtered-Instruction
|
| 11 |
+
- cognitivecomputations/dolphin-coder
|
| 12 |
+
- cognitivecomputations/samantha-data
|
| 13 |
+
- microsoft/orca-math-word-problems-200k
|
| 14 |
+
- Locutusque/function-calling-chatml
|
| 15 |
+
- internlm/Agent-FLAN
|
| 16 |
---
|
| 17 |
|
| 18 |
+
# Dolphin 2.9.3 Mistral Nemo 12b 🐬
|
| 19 |
+
|
| 20 |
+
Curated and trained by Eric Hartford and Cognitive Computations
|
| 21 |
+
|
| 22 |
+
[](https://discord.gg/h3K4XGj2RH)
|
| 23 |
+
Discord: https://discord.gg/h3K4XGj2RH
|
| 24 |
+
|
| 25 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/ldkN1J0WIDQwU4vutGYiD.png" width="600" />
|
| 26 |
+
|
| 27 |
+
Our appreciation for the sponsors of Dolphin 2.9.3:
|
| 28 |
+
- [Crusoe Cloud](https://crusoe.ai/) - provided excellent on-demand 8xL40S node
|
| 29 |
+
|
| 30 |
+
This model is based on mistralai/Mistral-Nemo-Base-2407, and is governed by the apache 2.0 license.
|
| 31 |
+
|
| 32 |
+
The base model has 128K context, and our finetuning used 8192 sequence length.
|
| 33 |
+
|
| 34 |
+
Dolphin 2.9.3 uses ChatML prompt template format.
|
| 35 |
+
|
| 36 |
+
example:
|
| 37 |
+
|
| 38 |
+
```
|
| 39 |
+
<|im_start|>system
|
| 40 |
+
You are Dolphin, a helpful AI assistant.<|im_end|>
|
| 41 |
+
<|im_start|>user
|
| 42 |
+
{prompt}<|im_end|>
|
| 43 |
+
<|im_start|>assistant
|
| 44 |
+
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
+
Dolphin-2.9.3 has a variety of instruction following, conversational, and coding skills. It also has initial agentic abilities and supports function calling.
|
| 48 |
+
|
| 49 |
+
Dolphin is uncensored. We 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.
|
| 50 |
+
|
| 51 |
+
Dolphin is licensed according to apache 2.0 license. We grant permission for any use, including commercial. Dolphin was trained on data generated from GPT4, among other models.
|
| 52 |
+
|
| 53 |
+
## Evals
|
| 54 |
+
|
| 55 |
+
TBD
|
| 56 |
+
|
| 57 |
+
## Training
|
| 58 |
+
|
| 59 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 60 |
should probably proofread and complete it, then remove this comment. -->
|
| 61 |
|