Update README.md
Browse files
README.md
CHANGED
@@ -7,44 +7,6 @@ tags:
|
|
7 |
- merge
|
8 |
|
9 |
---
|
10 |
-
#
|
11 |
|
12 |
-
|
13 |
-
|
14 |
-
## Merge Details
|
15 |
-
### Merge Method
|
16 |
-
|
17 |
-
This model was merged using the passthrough merge method.
|
18 |
-
|
19 |
-
### Models Merged
|
20 |
-
|
21 |
-
The following models were included in the merge:
|
22 |
-
* [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B)
|
23 |
-
|
24 |
-
### Configuration
|
25 |
-
|
26 |
-
The following YAML configuration was used to produce this model:
|
27 |
-
|
28 |
-
```yaml
|
29 |
-
slices:
|
30 |
-
- sources:
|
31 |
-
- layer_range: [0, 6]
|
32 |
-
model: Qwen/Qwen2.5-3B
|
33 |
-
- sources:
|
34 |
-
- layer_range: [3, 12]
|
35 |
-
model: Qwen/Qwen2.5-3B
|
36 |
-
- sources:
|
37 |
-
- layer_range: [9, 18]
|
38 |
-
model: Qwen/Qwen2.5-3B
|
39 |
-
- sources:
|
40 |
-
- layer_range: [14, 24]
|
41 |
-
model: Qwen/Qwen2.5-3B
|
42 |
-
- sources:
|
43 |
-
- layer_range: [20, 30]
|
44 |
-
model: Qwen/Qwen2.5-3B
|
45 |
-
- sources:
|
46 |
-
- layer_range: [26, 36]
|
47 |
-
model: Qwen/Qwen2.5-3B
|
48 |
-
merge_method: passthrough
|
49 |
-
dtype: bfloat16
|
50 |
-
```
|
|
|
7 |
- merge
|
8 |
|
9 |
---
|
10 |
+
# Qwark 4B
|
11 |
|
12 |
+
> any of a number of subatomic language models carrying 4 billion parameters, postulated as building blocks of small AI Agents. Qwarks have not been directly observed (until now) but theoretical predictions based on their existence have been confirmed experimentally.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|