Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,9 @@ My appreciation for the sponsors of Dolphin 2.8:
|
|
| 28 |
|
| 29 |
This model is based on [Mistral-7b-v0.2](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) a new base model released by MistralAI on March 23, 2024 but they have not yet published on HuggingFace. Thanks to @alpindale for converting / publishing.
|
| 30 |
|
| 31 |
-
The base model has 32k context, and the fine-tune was with 16k sequence lengths.
|
|
|
|
|
|
|
| 32 |
|
| 33 |
Dolphin-2.8 has a variety of instruction, conversational, and coding skills.
|
| 34 |
|
|
|
|
| 28 |
|
| 29 |
This model is based on [Mistral-7b-v0.2](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) a new base model released by MistralAI on March 23, 2024 but they have not yet published on HuggingFace. Thanks to @alpindale for converting / publishing.
|
| 30 |
|
| 31 |
+
The base model has 32k context, and the full-weights fine-tune was with 16k sequence lengths.
|
| 32 |
+
|
| 33 |
+
It took 3 days on 10x L40S provided by [Crusoe Cloud](https://crusoe.ai/)
|
| 34 |
|
| 35 |
Dolphin-2.8 has a variety of instruction, conversational, and coding skills.
|
| 36 |
|