Steelskull
commited on
Commit
•
07e18df
1
Parent(s):
897667b
Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
|
3 |
+
# Doc / guide: https://huggingface.co/docs/hub/model-cards
|
4 |
+
{}
|
5 |
+
---
|
6 |
+
|
7 |
+
# Model Card for Model ID
|
8 |
+
|
9 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
10 |
+
|
11 |
+
This model is an extreme experiment, I wanted to test making an MoE out of multiple High Performing Solar models. Let me know what you think
|
12 |
+
|
13 |
+
## Model Details
|
14 |
+
|
15 |
+
### Model Description
|
16 |
+
|
17 |
+
This MoE model is an extreme experiment, I wanted to test making an MoE out of multiple High Performing Solar models. Let me know what you think.
|
18 |
+
Thinking about finetuning on a RP dataset later on to direct the model more
|
19 |
+
|
20 |
+
- **Model type:** [More Information Needed]
|
21 |
+
|
22 |
+
### Model Sources [optional]
|
23 |
+
|
24 |
+
model_name: Lumosia-MoE-4x10.7
|
25 |
+
base_model: DopeorNope/SOLARC-M-10.7B
|
26 |
+
gate_mode: hidden
|
27 |
+
dtype: bfloat16
|
28 |
+
experts:
|
29 |
+
- source_model: DopeorNope/SOLARC-M-10.7B
|
30 |
+
positive_prompts: [""]
|
31 |
+
- source_model: maywell/PiVoT-10.7B-Mistral-v0.2-RP
|
32 |
+
positive_prompts: [""]
|
33 |
+
- source_model: kyujinpy/Sakura-SOLAR-Instruct
|
34 |
+
positive_prompts: [""]
|
35 |
+
- source_model: jeonsworld/CarbonVillain-en-10.7B-v1
|
36 |
+
positive_prompts: [""]
|
37 |
+
|