Commit
•
cb13d04
1
Parent(s):
24b4d0d
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,40 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: llama3
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
tags:
|
| 4 |
+
- moe
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
Experimental RP-oriented MoE, the idea was to get a model that would be equal to or better than Mixtral 8x7B and it's finetunes in RP/ERP tasks.
|
| 10 |
+
|
| 11 |
+
### Llama 3 SnowStorm 4x8B
|
| 12 |
+
```
|
| 13 |
+
base_model: NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS
|
| 14 |
+
gate_mode: random
|
| 15 |
+
dtype: bfloat16
|
| 16 |
+
experts_per_token: 2
|
| 17 |
+
experts:
|
| 18 |
+
- source_model: ChaoticNeutrals_Poppy_Porpoise-v0.7-L3-8B
|
| 19 |
+
- source_model: NeverSleep_Llama-3-Lumimaid-8B-v0.1-OAS
|
| 20 |
+
- source_model: openlynn_Llama-3-Soliloquy-8B-v2
|
| 21 |
+
- source_model: Sao10K_L3-8B-Stheno-v3.1
|
| 22 |
+
```
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
## Models used
|
| 26 |
+
|
| 27 |
+
- [ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B)
|
| 28 |
+
- [NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS](https://huggingface.co/NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS)
|
| 29 |
+
- [openlynn/Llama-3-Soliloquy-8B-v2](https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v2)
|
| 30 |
+
- [Sao10K/L3-8B-Stheno-v3.1](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.1)
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
## Vision
|
| 34 |
+
|
| 35 |
+
[llama3_mmproj](https://huggingface.co/ChaoticNeutrals/LLaVA-Llama-3-8B-mmproj-Updated)
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
## Prompt format: Llama 3
|