Yash Marathe
commited on
Commit
•
4c212c0
1
Parent(s):
1448d4d
Update README.md
Browse files
README.md
CHANGED
@@ -1,60 +1,16 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
tags:
|
4 |
-
-
|
5 |
-
- merge
|
6 |
-
- mergekit
|
7 |
-
- lazymergekit
|
8 |
-
- OpenPipe/mistral-ft-optimized-1227
|
9 |
-
- openchat/openchat-3.5-1210
|
10 |
-
- HuggingFaceH4/zephyr-7b-beta
|
11 |
-
- meta-math/MetaMath-Mistral-7B
|
12 |
---
|
13 |
|
14 |
# OpenMistral-MoE
|
15 |
|
16 |
-
OpenMistral-MoE is a Mixure of Experts (MoE)
|
17 |
* [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227)
|
18 |
* [openchat/openchat-3.5-1210](https://huggingface.co/openchat/openchat-3.5-1210)
|
19 |
* [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
|
20 |
* [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
|
21 |
|
22 |
-
## 🧩 Configuration
|
23 |
-
|
24 |
-
```yaml
|
25 |
-
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
26 |
-
gate_mode: hidden
|
27 |
-
dtype: bfloat16
|
28 |
-
merge_method: dare_ties
|
29 |
-
experts:
|
30 |
-
- source_model: OpenPipe/mistral-ft-optimized-1227
|
31 |
-
positive_prompts:
|
32 |
-
- "chat"
|
33 |
-
- "assistant"
|
34 |
-
- "tell me"
|
35 |
-
- "explain"
|
36 |
-
- source_model: openchat/openchat-3.5-1210
|
37 |
-
positive_prompts:
|
38 |
-
- "code"
|
39 |
-
- "python"
|
40 |
-
- "javascript"
|
41 |
-
- "programming"
|
42 |
-
- "algorithm"
|
43 |
-
- source_model: HuggingFaceH4/zephyr-7b-beta
|
44 |
-
positive_prompts:
|
45 |
-
- "storywriting"
|
46 |
-
- "write"
|
47 |
-
- "scene"
|
48 |
-
- "story"
|
49 |
-
- "character"
|
50 |
-
- source_model: meta-math/MetaMath-Mistral-7B
|
51 |
-
positive_prompts:
|
52 |
-
- "reason"
|
53 |
-
- "math"
|
54 |
-
- "mathematics"
|
55 |
-
- "solve"
|
56 |
-
- "count"
|
57 |
-
```
|
58 |
|
59 |
## 💻 Usage
|
60 |
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
+
- MoE
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
# OpenMistral-MoE
|
7 |
|
8 |
+
OpenMistral-MoE is a Mixure of Experts (MoE)
|
9 |
* [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227)
|
10 |
* [openchat/openchat-3.5-1210](https://huggingface.co/openchat/openchat-3.5-1210)
|
11 |
* [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
|
12 |
* [meta-math/MetaMath-Mistral-7B](https://huggingface.co/meta-math/MetaMath-Mistral-7B)
|
13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
## 💻 Usage
|
16 |
|