Update README.md
Browse files
README.md
CHANGED
@@ -2,40 +2,18 @@
|
|
2 |
base_model:
|
3 |
- unsloth/Mistral-Small-Instruct-2409
|
4 |
- unsloth/Mistral-Small-Instruct-2409
|
5 |
-
-
|
6 |
library_name: transformers
|
7 |
tags:
|
8 |
- mergekit
|
9 |
- merge
|
10 |
|
11 |
---
|
12 |
-
#
|
13 |
|
14 |
-
|
15 |
|
16 |
-
|
17 |
-
|
18 |
|
19 |
-
|
20 |
-
|
21 |
-
### Models Merged
|
22 |
-
|
23 |
-
The following models were included in the merge:
|
24 |
-
* [unsloth/Mistral-Small-Instruct-2409](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409)
|
25 |
-
* [unsloth/Mistral-Small-Instruct-2409](https://huggingface.co/unsloth/Mistral-Small-Instruct-2409) + [The-Company/Acolyte-LORA-Proper-e2](https://huggingface.co/The-Company/Acolyte-LORA-Proper-e2)
|
26 |
-
|
27 |
-
### Configuration
|
28 |
-
|
29 |
-
The following YAML configuration was used to produce this model:
|
30 |
-
|
31 |
-
```yaml
|
32 |
-
models:
|
33 |
-
- model: unsloth/Mistral-Small-Instruct-2409+The-Company/Acolyte-LORA-Proper-e2
|
34 |
-
- model: unsloth/Mistral-Small-Instruct-2409
|
35 |
-
merge_method: slerp
|
36 |
-
base_model: unsloth/Mistral-Small-Instruct-2409
|
37 |
-
parameters:
|
38 |
-
t: 0.5
|
39 |
-
dtype: bfloat16
|
40 |
-
|
41 |
-
```
|
|
|
2 |
base_model:
|
3 |
- unsloth/Mistral-Small-Instruct-2409
|
4 |
- unsloth/Mistral-Small-Instruct-2409
|
5 |
+
- rAIfle/Acolyte-LORA
|
6 |
library_name: transformers
|
7 |
tags:
|
8 |
- mergekit
|
9 |
- merge
|
10 |
|
11 |
---
|
12 |
+
# Acolyte-22B
|
13 |
|
14 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6569a4ed2419be6072890cf8/3dcGMcrWK2-2vQh9QBt3o.png)
|
15 |
|
16 |
+
LoRA of a bunch of random datasets on top of Mistral-Small-Instruct-2409, then SLERPed onto base at 0.5. Decent enough for its size.
|
17 |
+
Check the LoRA for dataset info.
|
18 |
|
19 |
+
Use `Mistral V2 & V3` template.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|