Update README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ My appreciation for the sponsor of Dolphin 2.9:
|
|
21 |
|
22 |
Crusoe Cloud - provided excellent on-demand 8xL40S node
|
23 |
|
24 |
-
This model is based on Llama-3-8b
|
25 |
|
26 |
The base model has 8k context, and the full-weight fine-tuning was with 8k sequence length.
|
27 |
|
@@ -156,24 +156,6 @@ tokens:
|
|
156 |
|
157 |
</details><br>
|
158 |
|
159 |
-
# out
|
160 |
-
|
161 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
162 |
-
It achieves the following results on the evaluation set:
|
163 |
-
- Loss: 0.6602
|
164 |
-
|
165 |
-
## Model description
|
166 |
-
|
167 |
-
More information needed
|
168 |
-
|
169 |
-
## Intended uses & limitations
|
170 |
-
|
171 |
-
More information needed
|
172 |
-
|
173 |
-
## Training and evaluation data
|
174 |
-
|
175 |
-
More information needed
|
176 |
-
|
177 |
## Training procedure
|
178 |
|
179 |
### Training hyperparameters
|
|
|
21 |
|
22 |
Crusoe Cloud - provided excellent on-demand 8xL40S node
|
23 |
|
24 |
+
This model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT
|
25 |
|
26 |
The base model has 8k context, and the full-weight fine-tuning was with 8k sequence length.
|
27 |
|
|
|
156 |
|
157 |
</details><br>
|
158 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
159 |
## Training procedure
|
160 |
|
161 |
### Training hyperparameters
|