Commit
•
7839dc1
1
Parent(s):
37be33b
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ language:
|
|
| 11 |
|
| 12 |
Experimental RP-oriented MoE, the idea was to get a model that would be equal to or better than the Mixtral 8x7B and it's finetunes in RP/ERP tasks.
|
| 13 |
|
|
|
|
|
|
|
| 14 |
Please feedback me if it's more stable than the [previous version](https://huggingface.co/xxx777xxxASD/L3-ChaoticSoliloquy-v1.5-4x8B)
|
| 15 |
|
| 16 |
### Llama 3 ChaoticSoliloquy-v2-4x8B test
|
|
|
|
| 11 |
|
| 12 |
Experimental RP-oriented MoE, the idea was to get a model that would be equal to or better than the Mixtral 8x7B and it's finetunes in RP/ERP tasks.
|
| 13 |
|
| 14 |
+
The model has totally 25B parameters, of which ~13B are active.
|
| 15 |
+
|
| 16 |
Please feedback me if it's more stable than the [previous version](https://huggingface.co/xxx777xxxASD/L3-ChaoticSoliloquy-v1.5-4x8B)
|
| 17 |
|
| 18 |
### Llama 3 ChaoticSoliloquy-v2-4x8B test
|