Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +1470 -0
- added_tokens.json +24 -0
- config.json +28 -0
- mergekit_config.yml +1438 -0
- merges.txt +0 -0
- model-00001-of-00119.safetensors +3 -0
- model-00002-of-00119.safetensors +3 -0
- model-00003-of-00119.safetensors +3 -0
- model-00004-of-00119.safetensors +3 -0
- model-00005-of-00119.safetensors +3 -0
- model-00006-of-00119.safetensors +3 -0
- model-00007-of-00119.safetensors +3 -0
- model-00008-of-00119.safetensors +3 -0
- model-00009-of-00119.safetensors +3 -0
- model-00010-of-00119.safetensors +3 -0
- model-00011-of-00119.safetensors +3 -0
- model-00012-of-00119.safetensors +3 -0
- model-00013-of-00119.safetensors +3 -0
- model-00014-of-00119.safetensors +3 -0
- model-00015-of-00119.safetensors +3 -0
- model-00016-of-00119.safetensors +3 -0
- model-00017-of-00119.safetensors +3 -0
- model-00018-of-00119.safetensors +3 -0
- model-00019-of-00119.safetensors +3 -0
- model-00020-of-00119.safetensors +3 -0
- model-00021-of-00119.safetensors +3 -0
- model-00022-of-00119.safetensors +3 -0
- model-00023-of-00119.safetensors +3 -0
- model-00024-of-00119.safetensors +3 -0
- model-00025-of-00119.safetensors +3 -0
- model-00026-of-00119.safetensors +3 -0
- model-00027-of-00119.safetensors +3 -0
- model-00028-of-00119.safetensors +3 -0
- model-00029-of-00119.safetensors +3 -0
- model-00030-of-00119.safetensors +3 -0
- model-00031-of-00119.safetensors +3 -0
- model-00032-of-00119.safetensors +3 -0
- model-00033-of-00119.safetensors +3 -0
- model-00034-of-00119.safetensors +3 -0
- model-00035-of-00119.safetensors +3 -0
- model-00036-of-00119.safetensors +3 -0
- model-00037-of-00119.safetensors +3 -0
- model-00038-of-00119.safetensors +3 -0
- model-00039-of-00119.safetensors +3 -0
- model-00040-of-00119.safetensors +3 -0
- model-00041-of-00119.safetensors +3 -0
- model-00042-of-00119.safetensors +3 -0
- model-00043-of-00119.safetensors +3 -0
- model-00044-of-00119.safetensors +3 -0
- model-00045-of-00119.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,1470 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- Qwen/Qwen2.5-72B-Instruct
|
4 |
+
- Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
|
10 |
+
---
|
11 |
+
# merge
|
12 |
+
|
13 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
+
|
15 |
+
## Merge Details
|
16 |
+
### Merge Method
|
17 |
+
|
18 |
+
This model was merged using the passthrough merge method.
|
19 |
+
|
20 |
+
### Models Merged
|
21 |
+
|
22 |
+
The following models were included in the merge:
|
23 |
+
* [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
|
24 |
+
* [Replete-AI/Replete-LLM-V2.5-Qwen-7b](https://huggingface.co/Replete-AI/Replete-LLM-V2.5-Qwen-7b)
|
25 |
+
|
26 |
+
### Configuration
|
27 |
+
|
28 |
+
The following YAML configuration was used to produce this model:
|
29 |
+
|
30 |
+
```yaml
|
31 |
+
slices:
|
32 |
+
# Replete-AI Layer 0, repeated 8 times
|
33 |
+
- sources:
|
34 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
35 |
+
layer_range: [0, 1]
|
36 |
+
- sources:
|
37 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
38 |
+
layer_range: [0, 1]
|
39 |
+
- sources:
|
40 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
41 |
+
layer_range: [0, 1]
|
42 |
+
- sources:
|
43 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
44 |
+
layer_range: [0, 1]
|
45 |
+
- sources:
|
46 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
47 |
+
layer_range: [0, 1]
|
48 |
+
- sources:
|
49 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
50 |
+
layer_range: [0, 1]
|
51 |
+
- sources:
|
52 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
53 |
+
layer_range: [0, 1]
|
54 |
+
- sources:
|
55 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
56 |
+
layer_range: [0, 1]
|
57 |
+
|
58 |
+
# Qwen 72B Layer 0, repeated 8 times
|
59 |
+
- sources:
|
60 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
61 |
+
layer_range: [0, 1]
|
62 |
+
- sources:
|
63 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
64 |
+
layer_range: [0, 1]
|
65 |
+
- sources:
|
66 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
67 |
+
layer_range: [0, 1]
|
68 |
+
- sources:
|
69 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
70 |
+
layer_range: [0, 1]
|
71 |
+
- sources:
|
72 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
73 |
+
layer_range: [0, 1]
|
74 |
+
- sources:
|
75 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
76 |
+
layer_range: [0, 1]
|
77 |
+
- sources:
|
78 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
79 |
+
layer_range: [0, 1]
|
80 |
+
- sources:
|
81 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
82 |
+
layer_range: [0, 1]
|
83 |
+
|
84 |
+
# Replete-AI Layer 1, repeated 8 times
|
85 |
+
- sources:
|
86 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
87 |
+
layer_range: [1, 2]
|
88 |
+
- sources:
|
89 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
90 |
+
layer_range: [1, 2]
|
91 |
+
- sources:
|
92 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
93 |
+
layer_range: [1, 2]
|
94 |
+
- sources:
|
95 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
96 |
+
layer_range: [1, 2]
|
97 |
+
- sources:
|
98 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
99 |
+
layer_range: [1, 2]
|
100 |
+
- sources:
|
101 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
102 |
+
layer_range: [1, 2]
|
103 |
+
- sources:
|
104 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
105 |
+
layer_range: [1, 2]
|
106 |
+
- sources:
|
107 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
108 |
+
layer_range: [1, 2]
|
109 |
+
|
110 |
+
# Qwen 72B Layer 1, repeated 8 times
|
111 |
+
- sources:
|
112 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
113 |
+
layer_range: [1, 2]
|
114 |
+
- sources:
|
115 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
116 |
+
layer_range: [1, 2]
|
117 |
+
- sources:
|
118 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
119 |
+
layer_range: [1, 2]
|
120 |
+
- sources:
|
121 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
122 |
+
layer_range: [1, 2]
|
123 |
+
- sources:
|
124 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
125 |
+
layer_range: [1, 2]
|
126 |
+
- sources:
|
127 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
128 |
+
layer_range: [1, 2]
|
129 |
+
- sources:
|
130 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
131 |
+
layer_range: [1, 2]
|
132 |
+
- sources:
|
133 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
134 |
+
layer_range: [1, 2]
|
135 |
+
|
136 |
+
# Replete-AI Layer 2, repeated 8 times
|
137 |
+
- sources:
|
138 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
139 |
+
layer_range: [2, 3]
|
140 |
+
- sources:
|
141 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
142 |
+
layer_range: [2, 3]
|
143 |
+
- sources:
|
144 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
145 |
+
layer_range: [2, 3]
|
146 |
+
- sources:
|
147 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
148 |
+
layer_range: [2, 3]
|
149 |
+
- sources:
|
150 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
151 |
+
layer_range: [2, 3]
|
152 |
+
- sources:
|
153 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
154 |
+
layer_range: [2, 3]
|
155 |
+
- sources:
|
156 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
157 |
+
layer_range: [2, 3]
|
158 |
+
- sources:
|
159 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
160 |
+
layer_range: [2, 3]
|
161 |
+
|
162 |
+
# Qwen 72B Layer 2, repeated 8 times
|
163 |
+
- sources:
|
164 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
165 |
+
layer_range: [2, 3]
|
166 |
+
- sources:
|
167 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
168 |
+
layer_range: [2, 3]
|
169 |
+
- sources:
|
170 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
171 |
+
layer_range: [2, 3]
|
172 |
+
- sources:
|
173 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
174 |
+
layer_range: [2, 3]
|
175 |
+
- sources:
|
176 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
177 |
+
layer_range: [2, 3]
|
178 |
+
- sources:
|
179 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
180 |
+
layer_range: [2, 3]
|
181 |
+
- sources:
|
182 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
183 |
+
layer_range: [2, 3]
|
184 |
+
- sources:
|
185 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
186 |
+
layer_range: [2, 3]
|
187 |
+
|
188 |
+
# Replete-AI Layer 3, repeated 8 times
|
189 |
+
- sources:
|
190 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
191 |
+
layer_range: [3, 4]
|
192 |
+
- sources:
|
193 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
194 |
+
layer_range: [3, 4]
|
195 |
+
- sources:
|
196 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
197 |
+
layer_range: [3, 4]
|
198 |
+
- sources:
|
199 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
200 |
+
layer_range: [3, 4]
|
201 |
+
- sources:
|
202 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
203 |
+
layer_range: [3, 4]
|
204 |
+
- sources:
|
205 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
206 |
+
layer_range: [3, 4]
|
207 |
+
- sources:
|
208 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
209 |
+
layer_range: [3, 4]
|
210 |
+
- sources:
|
211 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
212 |
+
layer_range: [3, 4]
|
213 |
+
|
214 |
+
# Qwen 72B Layer 3, repeated 8 times
|
215 |
+
- sources:
|
216 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
217 |
+
layer_range: [3, 4]
|
218 |
+
- sources:
|
219 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
220 |
+
layer_range: [3, 4]
|
221 |
+
- sources:
|
222 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
223 |
+
layer_range: [3, 4]
|
224 |
+
- sources:
|
225 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
226 |
+
layer_range: [3, 4]
|
227 |
+
- sources:
|
228 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
229 |
+
layer_range: [3, 4]
|
230 |
+
- sources:
|
231 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
232 |
+
layer_range: [3, 4]
|
233 |
+
- sources:
|
234 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
235 |
+
layer_range: [3, 4]
|
236 |
+
- sources:
|
237 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
238 |
+
layer_range: [3, 4]
|
239 |
+
|
240 |
+
# Replete-AI Layer 4, repeated 8 times
|
241 |
+
- sources:
|
242 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
243 |
+
layer_range: [4, 5]
|
244 |
+
- sources:
|
245 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
246 |
+
layer_range: [4, 5]
|
247 |
+
- sources:
|
248 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
249 |
+
layer_range: [4, 5]
|
250 |
+
- sources:
|
251 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
252 |
+
layer_range: [4, 5]
|
253 |
+
- sources:
|
254 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
255 |
+
layer_range: [4, 5]
|
256 |
+
- sources:
|
257 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
258 |
+
layer_range: [4, 5]
|
259 |
+
- sources:
|
260 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
261 |
+
layer_range: [4, 5]
|
262 |
+
- sources:
|
263 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
264 |
+
layer_range: [4, 5]
|
265 |
+
|
266 |
+
# Qwen 72B Layer 4, repeated 8 times
|
267 |
+
- sources:
|
268 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
269 |
+
layer_range: [4, 5]
|
270 |
+
- sources:
|
271 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
272 |
+
layer_range: [4, 5]
|
273 |
+
- sources:
|
274 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
275 |
+
layer_range: [4, 5]
|
276 |
+
- sources:
|
277 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
278 |
+
layer_range: [4, 5]
|
279 |
+
- sources:
|
280 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
281 |
+
layer_range: [4, 5]
|
282 |
+
- sources:
|
283 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
284 |
+
layer_range: [4, 5]
|
285 |
+
- sources:
|
286 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
287 |
+
layer_range: [4, 5]
|
288 |
+
- sources:
|
289 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
290 |
+
layer_range: [4, 5]
|
291 |
+
|
292 |
+
# Replete-AI Layer 5, repeated 8 times
|
293 |
+
- sources:
|
294 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
295 |
+
layer_range: [5, 6]
|
296 |
+
- sources:
|
297 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
298 |
+
layer_range: [5, 6]
|
299 |
+
- sources:
|
300 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
301 |
+
layer_range: [5, 6]
|
302 |
+
- sources:
|
303 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
304 |
+
layer_range: [5, 6]
|
305 |
+
- sources:
|
306 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
307 |
+
layer_range: [5, 6]
|
308 |
+
- sources:
|
309 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
310 |
+
layer_range: [5, 6]
|
311 |
+
- sources:
|
312 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
313 |
+
layer_range: [5, 6]
|
314 |
+
- sources:
|
315 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
316 |
+
layer_range: [5, 6]
|
317 |
+
|
318 |
+
# Qwen 72B Layer 5, repeated 8 times
|
319 |
+
- sources:
|
320 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
321 |
+
layer_range: [5, 6]
|
322 |
+
- sources:
|
323 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
324 |
+
layer_range: [5, 6]
|
325 |
+
- sources:
|
326 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
327 |
+
layer_range: [5, 6]
|
328 |
+
- sources:
|
329 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
330 |
+
layer_range: [5, 6]
|
331 |
+
- sources:
|
332 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
333 |
+
layer_range: [5, 6]
|
334 |
+
- sources:
|
335 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
336 |
+
layer_range: [5, 6]
|
337 |
+
- sources:
|
338 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
339 |
+
layer_range: [5, 6]
|
340 |
+
- sources:
|
341 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
342 |
+
layer_range: [5, 6]
|
343 |
+
|
344 |
+
# Replete-AI Layer 6, repeated 8 times
|
345 |
+
- sources:
|
346 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
347 |
+
layer_range: [6, 7]
|
348 |
+
- sources:
|
349 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
350 |
+
layer_range: [6, 7]
|
351 |
+
- sources:
|
352 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
353 |
+
layer_range: [6, 7]
|
354 |
+
- sources:
|
355 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
356 |
+
layer_range: [6, 7]
|
357 |
+
- sources:
|
358 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
359 |
+
layer_range: [6, 7]
|
360 |
+
- sources:
|
361 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
362 |
+
layer_range: [6, 7]
|
363 |
+
- sources:
|
364 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
365 |
+
layer_range: [6, 7]
|
366 |
+
- sources:
|
367 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
368 |
+
layer_range: [6, 7]
|
369 |
+
|
370 |
+
# Qwen 72B Layer 6, repeated 8 times
|
371 |
+
- sources:
|
372 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
373 |
+
layer_range: [6, 7]
|
374 |
+
- sources:
|
375 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
376 |
+
layer_range: [6, 7]
|
377 |
+
- sources:
|
378 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
379 |
+
layer_range: [6, 7]
|
380 |
+
- sources:
|
381 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
382 |
+
layer_range: [6, 7]
|
383 |
+
- sources:
|
384 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
385 |
+
layer_range: [6, 7]
|
386 |
+
- sources:
|
387 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
388 |
+
layer_range: [6, 7]
|
389 |
+
- sources:
|
390 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
391 |
+
layer_range: [6, 7]
|
392 |
+
- sources:
|
393 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
394 |
+
layer_range: [6, 7]
|
395 |
+
|
396 |
+
# Replete-AI Layer 7, repeated 8 times
|
397 |
+
- sources:
|
398 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
399 |
+
layer_range: [7, 8]
|
400 |
+
- sources:
|
401 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
402 |
+
layer_range: [7, 8]
|
403 |
+
- sources:
|
404 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
405 |
+
layer_range: [7, 8]
|
406 |
+
- sources:
|
407 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
408 |
+
layer_range: [7, 8]
|
409 |
+
- sources:
|
410 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
411 |
+
layer_range: [7, 8]
|
412 |
+
- sources:
|
413 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
414 |
+
layer_range: [7, 8]
|
415 |
+
- sources:
|
416 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
417 |
+
layer_range: [7, 8]
|
418 |
+
- sources:
|
419 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
420 |
+
layer_range: [7, 8]
|
421 |
+
|
422 |
+
# Qwen 72B Layer 7, repeated 8 times
|
423 |
+
- sources:
|
424 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
425 |
+
layer_range: [7, 8]
|
426 |
+
- sources:
|
427 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
428 |
+
layer_range: [7, 8]
|
429 |
+
- sources:
|
430 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
431 |
+
layer_range: [7, 8]
|
432 |
+
- sources:
|
433 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
434 |
+
layer_range: [7, 8]
|
435 |
+
- sources:
|
436 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
437 |
+
layer_range: [7, 8]
|
438 |
+
- sources:
|
439 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
440 |
+
layer_range: [7, 8]
|
441 |
+
- sources:
|
442 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
443 |
+
layer_range: [7, 8]
|
444 |
+
- sources:
|
445 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
446 |
+
layer_range: [7, 8]
|
447 |
+
|
448 |
+
# Replete-AI Layer 8, repeated 8 times
|
449 |
+
- sources:
|
450 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
451 |
+
layer_range: [8, 9]
|
452 |
+
- sources:
|
453 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
454 |
+
layer_range: [8, 9]
|
455 |
+
- sources:
|
456 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
457 |
+
layer_range: [8, 9]
|
458 |
+
- sources:
|
459 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
460 |
+
layer_range: [8, 9]
|
461 |
+
- sources:
|
462 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
463 |
+
layer_range: [8, 9]
|
464 |
+
- sources:
|
465 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
466 |
+
layer_range: [8, 9]
|
467 |
+
- sources:
|
468 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
469 |
+
layer_range: [8, 9]
|
470 |
+
- sources:
|
471 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
472 |
+
layer_range: [8, 9]
|
473 |
+
|
474 |
+
# Qwen 72B Layer 8, repeated 8 times
|
475 |
+
- sources:
|
476 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
477 |
+
layer_range: [8, 9]
|
478 |
+
- sources:
|
479 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
480 |
+
layer_range: [8, 9]
|
481 |
+
- sources:
|
482 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
483 |
+
layer_range: [8, 9]
|
484 |
+
- sources:
|
485 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
486 |
+
layer_range: [8, 9]
|
487 |
+
- sources:
|
488 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
489 |
+
layer_range: [8, 9]
|
490 |
+
- sources:
|
491 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
492 |
+
layer_range: [8, 9]
|
493 |
+
- sources:
|
494 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
495 |
+
layer_range: [8, 9]
|
496 |
+
- sources:
|
497 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
498 |
+
layer_range: [8, 9]
|
499 |
+
|
500 |
+
# Replete-AI Layer 9, repeated 8 times
|
501 |
+
- sources:
|
502 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
503 |
+
layer_range: [9, 10]
|
504 |
+
- sources:
|
505 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
506 |
+
layer_range: [9, 10]
|
507 |
+
- sources:
|
508 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
509 |
+
layer_range: [9, 10]
|
510 |
+
- sources:
|
511 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
512 |
+
layer_range: [9, 10]
|
513 |
+
- sources:
|
514 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
515 |
+
layer_range: [9, 10]
|
516 |
+
- sources:
|
517 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
518 |
+
layer_range: [9, 10]
|
519 |
+
- sources:
|
520 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
521 |
+
layer_range: [9, 10]
|
522 |
+
- sources:
|
523 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
524 |
+
layer_range: [9, 10]
|
525 |
+
|
526 |
+
# Qwen 72B Layer 9, repeated 8 times
|
527 |
+
- sources:
|
528 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
529 |
+
layer_range: [9, 10]
|
530 |
+
- sources:
|
531 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
532 |
+
layer_range: [9, 10]
|
533 |
+
- sources:
|
534 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
535 |
+
layer_range: [9, 10]
|
536 |
+
- sources:
|
537 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
538 |
+
layer_range: [9, 10]
|
539 |
+
- sources:
|
540 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
541 |
+
layer_range: [9, 10]
|
542 |
+
- sources:
|
543 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
544 |
+
layer_range: [9, 10]
|
545 |
+
- sources:
|
546 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
547 |
+
layer_range: [9, 10]
|
548 |
+
- sources:
|
549 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
550 |
+
layer_range: [9, 10]
|
551 |
+
|
552 |
+
# Replete-AI Layer 10, repeated 8 times
|
553 |
+
- sources:
|
554 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
555 |
+
layer_range: [10, 11]
|
556 |
+
- sources:
|
557 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
558 |
+
layer_range: [10, 11]
|
559 |
+
- sources:
|
560 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
561 |
+
layer_range: [10, 11]
|
562 |
+
- sources:
|
563 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
564 |
+
layer_range: [10, 11]
|
565 |
+
- sources:
|
566 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
567 |
+
layer_range: [10, 11]
|
568 |
+
- sources:
|
569 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
570 |
+
layer_range: [10, 11]
|
571 |
+
- sources:
|
572 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
573 |
+
layer_range: [10, 11]
|
574 |
+
- sources:
|
575 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
576 |
+
layer_range: [10, 11]
|
577 |
+
|
578 |
+
# Qwen 72B Layer 10, repeated 8 times
|
579 |
+
- sources:
|
580 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
581 |
+
layer_range: [10, 11]
|
582 |
+
- sources:
|
583 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
584 |
+
layer_range: [10, 11]
|
585 |
+
- sources:
|
586 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
587 |
+
layer_range: [10, 11]
|
588 |
+
- sources:
|
589 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
590 |
+
layer_range: [10, 11]
|
591 |
+
- sources:
|
592 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
593 |
+
layer_range: [10, 11]
|
594 |
+
- sources:
|
595 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
596 |
+
layer_range: [10, 11]
|
597 |
+
- sources:
|
598 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
599 |
+
layer_range: [10, 11]
|
600 |
+
- sources:
|
601 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
602 |
+
layer_range: [10, 11]
|
603 |
+
|
604 |
+
# Replete-AI Layer 11, repeated 8 times
|
605 |
+
- sources:
|
606 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
607 |
+
layer_range: [11, 12]
|
608 |
+
- sources:
|
609 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
610 |
+
layer_range: [11, 12]
|
611 |
+
- sources:
|
612 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
613 |
+
layer_range: [11, 12]
|
614 |
+
- sources:
|
615 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
616 |
+
layer_range: [11, 12]
|
617 |
+
- sources:
|
618 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
619 |
+
layer_range: [11, 12]
|
620 |
+
- sources:
|
621 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
622 |
+
layer_range: [11, 12]
|
623 |
+
- sources:
|
624 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
625 |
+
layer_range: [11, 12]
|
626 |
+
- sources:
|
627 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
628 |
+
layer_range: [11, 12]
|
629 |
+
|
630 |
+
# Qwen 72B Layer 11, repeated 8 times
|
631 |
+
- sources:
|
632 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
633 |
+
layer_range: [11, 12]
|
634 |
+
- sources:
|
635 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
636 |
+
layer_range: [11, 12]
|
637 |
+
- sources:
|
638 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
639 |
+
layer_range: [11, 12]
|
640 |
+
- sources:
|
641 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
642 |
+
layer_range: [11, 12]
|
643 |
+
- sources:
|
644 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
645 |
+
layer_range: [11, 12]
|
646 |
+
- sources:
|
647 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
648 |
+
layer_range: [11, 12]
|
649 |
+
- sources:
|
650 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
651 |
+
layer_range: [11, 12]
|
652 |
+
- sources:
|
653 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
654 |
+
layer_range: [11, 12]
|
655 |
+
|
656 |
+
# Replete-AI Layer 12, repeated 8 times
|
657 |
+
- sources:
|
658 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
659 |
+
layer_range: [12, 13]
|
660 |
+
- sources:
|
661 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
662 |
+
layer_range: [12, 13]
|
663 |
+
- sources:
|
664 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
665 |
+
layer_range: [12, 13]
|
666 |
+
- sources:
|
667 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
668 |
+
layer_range: [12, 13]
|
669 |
+
- sources:
|
670 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
671 |
+
layer_range: [12, 13]
|
672 |
+
- sources:
|
673 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
674 |
+
layer_range: [12, 13]
|
675 |
+
- sources:
|
676 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
677 |
+
layer_range: [12, 13]
|
678 |
+
- sources:
|
679 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
680 |
+
layer_range: [12, 13]
|
681 |
+
|
682 |
+
# Qwen 72B Layer 12, repeated 8 times
|
683 |
+
- sources:
|
684 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
685 |
+
layer_range: [12, 13]
|
686 |
+
- sources:
|
687 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
688 |
+
layer_range: [12, 13]
|
689 |
+
- sources:
|
690 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
691 |
+
layer_range: [12, 13]
|
692 |
+
- sources:
|
693 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
694 |
+
layer_range: [12, 13]
|
695 |
+
- sources:
|
696 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
697 |
+
layer_range: [12, 13]
|
698 |
+
- sources:
|
699 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
700 |
+
layer_range: [12, 13]
|
701 |
+
- sources:
|
702 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
703 |
+
layer_range: [12, 13]
|
704 |
+
- sources:
|
705 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
706 |
+
layer_range: [12, 13]
|
707 |
+
|
708 |
+
# Replete-AI Layer 13, repeated 8 times
|
709 |
+
- sources:
|
710 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
711 |
+
layer_range: [13, 14]
|
712 |
+
- sources:
|
713 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
714 |
+
layer_range: [13, 14]
|
715 |
+
- sources:
|
716 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
717 |
+
layer_range: [13, 14]
|
718 |
+
- sources:
|
719 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
720 |
+
layer_range: [13, 14]
|
721 |
+
- sources:
|
722 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
723 |
+
layer_range: [13, 14]
|
724 |
+
- sources:
|
725 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
726 |
+
layer_range: [13, 14]
|
727 |
+
- sources:
|
728 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
729 |
+
layer_range: [13, 14]
|
730 |
+
- sources:
|
731 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
732 |
+
layer_range: [13, 14]
|
733 |
+
|
734 |
+
# Qwen 72B Layer 13, repeated 8 times
|
735 |
+
- sources:
|
736 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
737 |
+
layer_range: [13, 14]
|
738 |
+
- sources:
|
739 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
740 |
+
layer_range: [13, 14]
|
741 |
+
- sources:
|
742 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
743 |
+
layer_range: [13, 14]
|
744 |
+
- sources:
|
745 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
746 |
+
layer_range: [13, 14]
|
747 |
+
- sources:
|
748 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
749 |
+
layer_range: [13, 14]
|
750 |
+
- sources:
|
751 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
752 |
+
layer_range: [13, 14]
|
753 |
+
- sources:
|
754 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
755 |
+
layer_range: [13, 14]
|
756 |
+
- sources:
|
757 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
758 |
+
layer_range: [13, 14]
|
759 |
+
|
760 |
+
# Replete-AI Layer 14, repeated 8 times
|
761 |
+
- sources:
|
762 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
763 |
+
layer_range: [14, 15]
|
764 |
+
- sources:
|
765 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
766 |
+
layer_range: [14, 15]
|
767 |
+
- sources:
|
768 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
769 |
+
layer_range: [14, 15]
|
770 |
+
- sources:
|
771 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
772 |
+
layer_range: [14, 15]
|
773 |
+
- sources:
|
774 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
775 |
+
layer_range: [14, 15]
|
776 |
+
- sources:
|
777 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
778 |
+
layer_range: [14, 15]
|
779 |
+
- sources:
|
780 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
781 |
+
layer_range: [14, 15]
|
782 |
+
- sources:
|
783 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
784 |
+
layer_range: [14, 15]
|
785 |
+
|
786 |
+
# Qwen 72B Layer 14, repeated 8 times
|
787 |
+
- sources:
|
788 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
789 |
+
layer_range: [14, 15]
|
790 |
+
- sources:
|
791 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
792 |
+
layer_range: [14, 15]
|
793 |
+
- sources:
|
794 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
795 |
+
layer_range: [14, 15]
|
796 |
+
- sources:
|
797 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
798 |
+
layer_range: [14, 15]
|
799 |
+
- sources:
|
800 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
801 |
+
layer_range: [14, 15]
|
802 |
+
- sources:
|
803 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
804 |
+
layer_range: [14, 15]
|
805 |
+
- sources:
|
806 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
807 |
+
layer_range: [14, 15]
|
808 |
+
- sources:
|
809 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
810 |
+
layer_range: [14, 15]
|
811 |
+
|
812 |
+
# Replete-AI Layer 15, repeated 8 times
|
813 |
+
- sources:
|
814 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
815 |
+
layer_range: [15, 16]
|
816 |
+
- sources:
|
817 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
818 |
+
layer_range: [15, 16]
|
819 |
+
- sources:
|
820 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
821 |
+
layer_range: [15, 16]
|
822 |
+
- sources:
|
823 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
824 |
+
layer_range: [15, 16]
|
825 |
+
- sources:
|
826 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
827 |
+
layer_range: [15, 16]
|
828 |
+
- sources:
|
829 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
830 |
+
layer_range: [15, 16]
|
831 |
+
- sources:
|
832 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
833 |
+
layer_range: [15, 16]
|
834 |
+
- sources:
|
835 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
836 |
+
layer_range: [15, 16]
|
837 |
+
|
838 |
+
# Qwen 72B Layer 15, repeated 8 times
|
839 |
+
- sources:
|
840 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
841 |
+
layer_range: [15, 16]
|
842 |
+
- sources:
|
843 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
844 |
+
layer_range: [15, 16]
|
845 |
+
- sources:
|
846 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
847 |
+
layer_range: [15, 16]
|
848 |
+
- sources:
|
849 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
850 |
+
layer_range: [15, 16]
|
851 |
+
- sources:
|
852 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
853 |
+
layer_range: [15, 16]
|
854 |
+
- sources:
|
855 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
856 |
+
layer_range: [15, 16]
|
857 |
+
- sources:
|
858 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
859 |
+
layer_range: [15, 16]
|
860 |
+
- sources:
|
861 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
862 |
+
layer_range: [15, 16]
|
863 |
+
|
864 |
+
# Replete-AI Layer 16, repeated 8 times
|
865 |
+
- sources:
|
866 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
867 |
+
layer_range: [16, 17]
|
868 |
+
- sources:
|
869 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
870 |
+
layer_range: [16, 17]
|
871 |
+
- sources:
|
872 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
873 |
+
layer_range: [16, 17]
|
874 |
+
- sources:
|
875 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
876 |
+
layer_range: [16, 17]
|
877 |
+
- sources:
|
878 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
879 |
+
layer_range: [16, 17]
|
880 |
+
- sources:
|
881 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
882 |
+
layer_range: [16, 17]
|
883 |
+
- sources:
|
884 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
885 |
+
layer_range: [16, 17]
|
886 |
+
- sources:
|
887 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
888 |
+
layer_range: [16, 17]
|
889 |
+
|
890 |
+
# Qwen 72B Layer 16, repeated 8 times
|
891 |
+
- sources:
|
892 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
893 |
+
layer_range: [16, 17]
|
894 |
+
- sources:
|
895 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
896 |
+
layer_range: [16, 17]
|
897 |
+
- sources:
|
898 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
899 |
+
layer_range: [16, 17]
|
900 |
+
- sources:
|
901 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
902 |
+
layer_range: [16, 17]
|
903 |
+
- sources:
|
904 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
905 |
+
layer_range: [16, 17]
|
906 |
+
- sources:
|
907 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
908 |
+
layer_range: [16, 17]
|
909 |
+
- sources:
|
910 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
911 |
+
layer_range: [16, 17]
|
912 |
+
- sources:
|
913 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
914 |
+
layer_range: [16, 17]
|
915 |
+
|
916 |
+
# Replete-AI Layer 17, repeated 8 times
|
917 |
+
- sources:
|
918 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
919 |
+
layer_range: [17, 18]
|
920 |
+
- sources:
|
921 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
922 |
+
layer_range: [17, 18]
|
923 |
+
- sources:
|
924 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
925 |
+
layer_range: [17, 18]
|
926 |
+
- sources:
|
927 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
928 |
+
layer_range: [17, 18]
|
929 |
+
- sources:
|
930 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
931 |
+
layer_range: [17, 18]
|
932 |
+
- sources:
|
933 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
934 |
+
layer_range: [17, 18]
|
935 |
+
- sources:
|
936 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
937 |
+
layer_range: [17, 18]
|
938 |
+
- sources:
|
939 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
940 |
+
layer_range: [17, 18]
|
941 |
+
|
942 |
+
# Qwen 72B Layer 17, repeated 8 times
|
943 |
+
- sources:
|
944 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
945 |
+
layer_range: [17, 18]
|
946 |
+
- sources:
|
947 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
948 |
+
layer_range: [17, 18]
|
949 |
+
- sources:
|
950 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
951 |
+
layer_range: [17, 18]
|
952 |
+
- sources:
|
953 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
954 |
+
layer_range: [17, 18]
|
955 |
+
- sources:
|
956 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
957 |
+
layer_range: [17, 18]
|
958 |
+
- sources:
|
959 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
960 |
+
layer_range: [17, 18]
|
961 |
+
- sources:
|
962 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
963 |
+
layer_range: [17, 18]
|
964 |
+
- sources:
|
965 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
966 |
+
layer_range: [17, 18]
|
967 |
+
|
968 |
+
# Replete-AI Layer 18, repeated 8 times
|
969 |
+
- sources:
|
970 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
971 |
+
layer_range: [18, 19]
|
972 |
+
- sources:
|
973 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
974 |
+
layer_range: [18, 19]
|
975 |
+
- sources:
|
976 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
977 |
+
layer_range: [18, 19]
|
978 |
+
- sources:
|
979 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
980 |
+
layer_range: [18, 19]
|
981 |
+
- sources:
|
982 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
983 |
+
layer_range: [18, 19]
|
984 |
+
- sources:
|
985 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
986 |
+
layer_range: [18, 19]
|
987 |
+
- sources:
|
988 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
989 |
+
layer_range: [18, 19]
|
990 |
+
- sources:
|
991 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
992 |
+
layer_range: [18, 19]
|
993 |
+
|
994 |
+
# Qwen 72B Layer 18, repeated 8 times
|
995 |
+
- sources:
|
996 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
997 |
+
layer_range: [18, 19]
|
998 |
+
- sources:
|
999 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1000 |
+
layer_range: [18, 19]
|
1001 |
+
- sources:
|
1002 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1003 |
+
layer_range: [18, 19]
|
1004 |
+
- sources:
|
1005 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1006 |
+
layer_range: [18, 19]
|
1007 |
+
- sources:
|
1008 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1009 |
+
layer_range: [18, 19]
|
1010 |
+
- sources:
|
1011 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1012 |
+
layer_range: [18, 19]
|
1013 |
+
- sources:
|
1014 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1015 |
+
layer_range: [18, 19]
|
1016 |
+
- sources:
|
1017 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1018 |
+
layer_range: [18, 19]
|
1019 |
+
|
1020 |
+
# Replete-AI Layer 19, repeated 8 times
|
1021 |
+
- sources:
|
1022 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1023 |
+
layer_range: [19, 20]
|
1024 |
+
- sources:
|
1025 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1026 |
+
layer_range: [19, 20]
|
1027 |
+
- sources:
|
1028 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1029 |
+
layer_range: [19, 20]
|
1030 |
+
- sources:
|
1031 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1032 |
+
layer_range: [19, 20]
|
1033 |
+
- sources:
|
1034 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1035 |
+
layer_range: [19, 20]
|
1036 |
+
- sources:
|
1037 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1038 |
+
layer_range: [19, 20]
|
1039 |
+
- sources:
|
1040 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1041 |
+
layer_range: [19, 20]
|
1042 |
+
- sources:
|
1043 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1044 |
+
layer_range: [19, 20]
|
1045 |
+
|
1046 |
+
# Qwen 72B Layer 19, repeated 8 times
|
1047 |
+
- sources:
|
1048 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1049 |
+
layer_range: [19, 20]
|
1050 |
+
- sources:
|
1051 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1052 |
+
layer_range: [19, 20]
|
1053 |
+
- sources:
|
1054 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1055 |
+
layer_range: [19, 20]
|
1056 |
+
- sources:
|
1057 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1058 |
+
layer_range: [19, 20]
|
1059 |
+
- sources:
|
1060 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1061 |
+
layer_range: [19, 20]
|
1062 |
+
- sources:
|
1063 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1064 |
+
layer_range: [19, 20]
|
1065 |
+
- sources:
|
1066 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1067 |
+
layer_range: [19, 20]
|
1068 |
+
- sources:
|
1069 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1070 |
+
layer_range: [19, 20]
|
1071 |
+
|
1072 |
+
# Replete-AI Layer 20, repeated 8 times
|
1073 |
+
- sources:
|
1074 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1075 |
+
layer_range: [20, 21]
|
1076 |
+
- sources:
|
1077 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1078 |
+
layer_range: [20, 21]
|
1079 |
+
- sources:
|
1080 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1081 |
+
layer_range: [20, 21]
|
1082 |
+
- sources:
|
1083 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1084 |
+
layer_range: [20, 21]
|
1085 |
+
- sources:
|
1086 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1087 |
+
layer_range: [20, 21]
|
1088 |
+
- sources:
|
1089 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1090 |
+
layer_range: [20, 21]
|
1091 |
+
- sources:
|
1092 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1093 |
+
layer_range: [20, 21]
|
1094 |
+
- sources:
|
1095 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1096 |
+
layer_range: [20, 21]
|
1097 |
+
|
1098 |
+
# Qwen 72B Layer 20, repeated 8 times
|
1099 |
+
- sources:
|
1100 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1101 |
+
layer_range: [20, 21]
|
1102 |
+
- sources:
|
1103 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1104 |
+
layer_range: [20, 21]
|
1105 |
+
- sources:
|
1106 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1107 |
+
layer_range: [20, 21]
|
1108 |
+
- sources:
|
1109 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1110 |
+
layer_range: [20, 21]
|
1111 |
+
- sources:
|
1112 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1113 |
+
layer_range: [20, 21]
|
1114 |
+
- sources:
|
1115 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1116 |
+
layer_range: [20, 21]
|
1117 |
+
- sources:
|
1118 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1119 |
+
layer_range: [20, 21]
|
1120 |
+
- sources:
|
1121 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1122 |
+
layer_range: [20, 21]
|
1123 |
+
|
1124 |
+
# Replete-AI Layer 21, repeated 8 times
|
1125 |
+
- sources:
|
1126 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1127 |
+
layer_range: [21, 22]
|
1128 |
+
- sources:
|
1129 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1130 |
+
layer_range: [21, 22]
|
1131 |
+
- sources:
|
1132 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1133 |
+
layer_range: [21, 22]
|
1134 |
+
- sources:
|
1135 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1136 |
+
layer_range: [21, 22]
|
1137 |
+
- sources:
|
1138 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1139 |
+
layer_range: [21, 22]
|
1140 |
+
- sources:
|
1141 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1142 |
+
layer_range: [21, 22]
|
1143 |
+
- sources:
|
1144 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1145 |
+
layer_range: [21, 22]
|
1146 |
+
- sources:
|
1147 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1148 |
+
layer_range: [21, 22]
|
1149 |
+
|
1150 |
+
# Qwen 72B Layer 21, repeated 8 times
|
1151 |
+
- sources:
|
1152 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1153 |
+
layer_range: [21, 22]
|
1154 |
+
- sources:
|
1155 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1156 |
+
layer_range: [21, 22]
|
1157 |
+
- sources:
|
1158 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1159 |
+
layer_range: [21, 22]
|
1160 |
+
- sources:
|
1161 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1162 |
+
layer_range: [21, 22]
|
1163 |
+
- sources:
|
1164 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1165 |
+
layer_range: [21, 22]
|
1166 |
+
- sources:
|
1167 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1168 |
+
layer_range: [21, 22]
|
1169 |
+
- sources:
|
1170 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1171 |
+
layer_range: [21, 22]
|
1172 |
+
- sources:
|
1173 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1174 |
+
layer_range: [21, 22]
|
1175 |
+
|
1176 |
+
# Replete-AI Layer 22, repeated 8 times
|
1177 |
+
- sources:
|
1178 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1179 |
+
layer_range: [22, 23]
|
1180 |
+
- sources:
|
1181 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1182 |
+
layer_range: [22, 23]
|
1183 |
+
- sources:
|
1184 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1185 |
+
layer_range: [22, 23]
|
1186 |
+
- sources:
|
1187 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1188 |
+
layer_range: [22, 23]
|
1189 |
+
- sources:
|
1190 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1191 |
+
layer_range: [22, 23]
|
1192 |
+
- sources:
|
1193 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1194 |
+
layer_range: [22, 23]
|
1195 |
+
- sources:
|
1196 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1197 |
+
layer_range: [22, 23]
|
1198 |
+
- sources:
|
1199 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1200 |
+
layer_range: [22, 23]
|
1201 |
+
|
1202 |
+
# Qwen 72B Layer 22, repeated 8 times
|
1203 |
+
- sources:
|
1204 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1205 |
+
layer_range: [22, 23]
|
1206 |
+
- sources:
|
1207 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1208 |
+
layer_range: [22, 23]
|
1209 |
+
- sources:
|
1210 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1211 |
+
layer_range: [22, 23]
|
1212 |
+
- sources:
|
1213 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1214 |
+
layer_range: [22, 23]
|
1215 |
+
- sources:
|
1216 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1217 |
+
layer_range: [22, 23]
|
1218 |
+
- sources:
|
1219 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1220 |
+
layer_range: [22, 23]
|
1221 |
+
- sources:
|
1222 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1223 |
+
layer_range: [22, 23]
|
1224 |
+
- sources:
|
1225 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1226 |
+
layer_range: [22, 23]
|
1227 |
+
|
1228 |
+
# Replete-AI Layer 23, repeated 8 times
|
1229 |
+
- sources:
|
1230 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1231 |
+
layer_range: [23, 24]
|
1232 |
+
- sources:
|
1233 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1234 |
+
layer_range: [23, 24]
|
1235 |
+
- sources:
|
1236 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1237 |
+
layer_range: [23, 24]
|
1238 |
+
- sources:
|
1239 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1240 |
+
layer_range: [23, 24]
|
1241 |
+
- sources:
|
1242 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1243 |
+
layer_range: [23, 24]
|
1244 |
+
- sources:
|
1245 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1246 |
+
layer_range: [23, 24]
|
1247 |
+
- sources:
|
1248 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1249 |
+
layer_range: [23, 24]
|
1250 |
+
- sources:
|
1251 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1252 |
+
layer_range: [23, 24]
|
1253 |
+
|
1254 |
+
# Qwen 72B Layer 23, repeated 8 times
|
1255 |
+
- sources:
|
1256 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1257 |
+
layer_range: [23, 24]
|
1258 |
+
- sources:
|
1259 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1260 |
+
layer_range: [23, 24]
|
1261 |
+
- sources:
|
1262 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1263 |
+
layer_range: [23, 24]
|
1264 |
+
- sources:
|
1265 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1266 |
+
layer_range: [23, 24]
|
1267 |
+
- sources:
|
1268 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1269 |
+
layer_range: [23, 24]
|
1270 |
+
- sources:
|
1271 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1272 |
+
layer_range: [23, 24]
|
1273 |
+
- sources:
|
1274 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1275 |
+
layer_range: [23, 24]
|
1276 |
+
- sources:
|
1277 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1278 |
+
layer_range: [23, 24]
|
1279 |
+
|
1280 |
+
# Replete-AI Layer 24, repeated 8 times
|
1281 |
+
- sources:
|
1282 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1283 |
+
layer_range: [24, 25]
|
1284 |
+
- sources:
|
1285 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1286 |
+
layer_range: [24, 25]
|
1287 |
+
- sources:
|
1288 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1289 |
+
layer_range: [24, 25]
|
1290 |
+
- sources:
|
1291 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1292 |
+
layer_range: [24, 25]
|
1293 |
+
- sources:
|
1294 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1295 |
+
layer_range: [24, 25]
|
1296 |
+
- sources:
|
1297 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1298 |
+
layer_range: [24, 25]
|
1299 |
+
- sources:
|
1300 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1301 |
+
layer_range: [24, 25]
|
1302 |
+
- sources:
|
1303 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1304 |
+
layer_range: [24, 25]
|
1305 |
+
|
1306 |
+
# Qwen 72B Layer 24, repeated 8 times
|
1307 |
+
- sources:
|
1308 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1309 |
+
layer_range: [24, 25]
|
1310 |
+
- sources:
|
1311 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1312 |
+
layer_range: [24, 25]
|
1313 |
+
- sources:
|
1314 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1315 |
+
layer_range: [24, 25]
|
1316 |
+
- sources:
|
1317 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1318 |
+
layer_range: [24, 25]
|
1319 |
+
- sources:
|
1320 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1321 |
+
layer_range: [24, 25]
|
1322 |
+
- sources:
|
1323 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1324 |
+
layer_range: [24, 25]
|
1325 |
+
- sources:
|
1326 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1327 |
+
layer_range: [24, 25]
|
1328 |
+
- sources:
|
1329 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1330 |
+
layer_range: [24, 25]
|
1331 |
+
|
1332 |
+
# Replete-AI Layer 25, repeated 8 times
|
1333 |
+
- sources:
|
1334 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1335 |
+
layer_range: [25, 26]
|
1336 |
+
- sources:
|
1337 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1338 |
+
layer_range: [25, 26]
|
1339 |
+
- sources:
|
1340 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1341 |
+
layer_range: [25, 26]
|
1342 |
+
- sources:
|
1343 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1344 |
+
layer_range: [25, 26]
|
1345 |
+
- sources:
|
1346 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1347 |
+
layer_range: [25, 26]
|
1348 |
+
- sources:
|
1349 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1350 |
+
layer_range: [25, 26]
|
1351 |
+
- sources:
|
1352 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1353 |
+
layer_range: [25, 26]
|
1354 |
+
- sources:
|
1355 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1356 |
+
layer_range: [25, 26]
|
1357 |
+
|
1358 |
+
# Qwen 72B Layer 25, repeated 8 times
|
1359 |
+
- sources:
|
1360 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1361 |
+
layer_range: [25, 26]
|
1362 |
+
- sources:
|
1363 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1364 |
+
layer_range: [25, 26]
|
1365 |
+
- sources:
|
1366 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1367 |
+
layer_range: [25, 26]
|
1368 |
+
- sources:
|
1369 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1370 |
+
layer_range: [25, 26]
|
1371 |
+
- sources:
|
1372 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1373 |
+
layer_range: [25, 26]
|
1374 |
+
- sources:
|
1375 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1376 |
+
layer_range: [25, 26]
|
1377 |
+
- sources:
|
1378 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1379 |
+
layer_range: [25, 26]
|
1380 |
+
- sources:
|
1381 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1382 |
+
layer_range: [25, 26]
|
1383 |
+
|
1384 |
+
# Replete-AI Layer 26, repeated 8 times
|
1385 |
+
- sources:
|
1386 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1387 |
+
layer_range: [26, 27]
|
1388 |
+
- sources:
|
1389 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1390 |
+
layer_range: [26, 27]
|
1391 |
+
- sources:
|
1392 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1393 |
+
layer_range: [26, 27]
|
1394 |
+
- sources:
|
1395 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1396 |
+
layer_range: [26, 27]
|
1397 |
+
- sources:
|
1398 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1399 |
+
layer_range: [26, 27]
|
1400 |
+
- sources:
|
1401 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1402 |
+
layer_range: [26, 27]
|
1403 |
+
- sources:
|
1404 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1405 |
+
layer_range: [26, 27]
|
1406 |
+
- sources:
|
1407 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1408 |
+
layer_range: [26, 27]
|
1409 |
+
|
1410 |
+
# Qwen 72B Layer 26, repeated 8 times
|
1411 |
+
- sources:
|
1412 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1413 |
+
layer_range: [26, 27]
|
1414 |
+
- sources:
|
1415 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1416 |
+
layer_range: [26, 27]
|
1417 |
+
- sources:
|
1418 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1419 |
+
layer_range: [26, 27]
|
1420 |
+
- sources:
|
1421 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1422 |
+
layer_range: [26, 27]
|
1423 |
+
- sources:
|
1424 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1425 |
+
layer_range: [26, 27]
|
1426 |
+
- sources:
|
1427 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1428 |
+
layer_range: [26, 27]
|
1429 |
+
- sources:
|
1430 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1431 |
+
layer_range: [26, 27]
|
1432 |
+
- sources:
|
1433 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1434 |
+
layer_range: [26, 27]
|
1435 |
+
|
1436 |
+
# Replete-AI Layer 27, repeated 8 times
|
1437 |
+
- sources:
|
1438 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1439 |
+
layer_range: [27, 28]
|
1440 |
+
- sources:
|
1441 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1442 |
+
layer_range: [27, 28]
|
1443 |
+
- sources:
|
1444 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1445 |
+
layer_range: [27, 28]
|
1446 |
+
- sources:
|
1447 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1448 |
+
layer_range: [27, 28]
|
1449 |
+
- sources:
|
1450 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1451 |
+
layer_range: [27, 28]
|
1452 |
+
- sources:
|
1453 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1454 |
+
layer_range: [27, 28]
|
1455 |
+
- sources:
|
1456 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1457 |
+
layer_range: [27, 28]
|
1458 |
+
- sources:
|
1459 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1460 |
+
layer_range: [27, 28]
|
1461 |
+
|
1462 |
+
# Qwen 72B Layer 27, repeated 8 times
|
1463 |
+
- sources:
|
1464 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1465 |
+
layer_range: [27, 80]
|
1466 |
+
|
1467 |
+
merge_method: passthrough
|
1468 |
+
dtype: float16
|
1469 |
+
|
1470 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen2.5-72B-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151645,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 8192,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 29568,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 70,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"num_attention_heads": 64,
|
17 |
+
"num_hidden_layers": 493,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"rms_norm_eps": 1e-06,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": null,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float16",
|
24 |
+
"transformers_version": "4.44.1",
|
25 |
+
"use_cache": true,
|
26 |
+
"use_sliding_window": false,
|
27 |
+
"vocab_size": 152064
|
28 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,1438 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices:
|
2 |
+
# Replete-AI Layer 0, repeated 8 times
|
3 |
+
- sources:
|
4 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
5 |
+
layer_range: [0, 1]
|
6 |
+
- sources:
|
7 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
8 |
+
layer_range: [0, 1]
|
9 |
+
- sources:
|
10 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
11 |
+
layer_range: [0, 1]
|
12 |
+
- sources:
|
13 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
14 |
+
layer_range: [0, 1]
|
15 |
+
- sources:
|
16 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
17 |
+
layer_range: [0, 1]
|
18 |
+
- sources:
|
19 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
20 |
+
layer_range: [0, 1]
|
21 |
+
- sources:
|
22 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
23 |
+
layer_range: [0, 1]
|
24 |
+
- sources:
|
25 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
26 |
+
layer_range: [0, 1]
|
27 |
+
|
28 |
+
# Qwen 72B Layer 0, repeated 8 times
|
29 |
+
- sources:
|
30 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
31 |
+
layer_range: [0, 1]
|
32 |
+
- sources:
|
33 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
34 |
+
layer_range: [0, 1]
|
35 |
+
- sources:
|
36 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
37 |
+
layer_range: [0, 1]
|
38 |
+
- sources:
|
39 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
40 |
+
layer_range: [0, 1]
|
41 |
+
- sources:
|
42 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
43 |
+
layer_range: [0, 1]
|
44 |
+
- sources:
|
45 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
46 |
+
layer_range: [0, 1]
|
47 |
+
- sources:
|
48 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
49 |
+
layer_range: [0, 1]
|
50 |
+
- sources:
|
51 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
52 |
+
layer_range: [0, 1]
|
53 |
+
|
54 |
+
# Replete-AI Layer 1, repeated 8 times
|
55 |
+
- sources:
|
56 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
57 |
+
layer_range: [1, 2]
|
58 |
+
- sources:
|
59 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
60 |
+
layer_range: [1, 2]
|
61 |
+
- sources:
|
62 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
63 |
+
layer_range: [1, 2]
|
64 |
+
- sources:
|
65 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
66 |
+
layer_range: [1, 2]
|
67 |
+
- sources:
|
68 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
69 |
+
layer_range: [1, 2]
|
70 |
+
- sources:
|
71 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
72 |
+
layer_range: [1, 2]
|
73 |
+
- sources:
|
74 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
75 |
+
layer_range: [1, 2]
|
76 |
+
- sources:
|
77 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
78 |
+
layer_range: [1, 2]
|
79 |
+
|
80 |
+
# Qwen 72B Layer 1, repeated 8 times
|
81 |
+
- sources:
|
82 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
83 |
+
layer_range: [1, 2]
|
84 |
+
- sources:
|
85 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
86 |
+
layer_range: [1, 2]
|
87 |
+
- sources:
|
88 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
89 |
+
layer_range: [1, 2]
|
90 |
+
- sources:
|
91 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
92 |
+
layer_range: [1, 2]
|
93 |
+
- sources:
|
94 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
95 |
+
layer_range: [1, 2]
|
96 |
+
- sources:
|
97 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
98 |
+
layer_range: [1, 2]
|
99 |
+
- sources:
|
100 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
101 |
+
layer_range: [1, 2]
|
102 |
+
- sources:
|
103 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
104 |
+
layer_range: [1, 2]
|
105 |
+
|
106 |
+
# Replete-AI Layer 2, repeated 8 times
|
107 |
+
- sources:
|
108 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
109 |
+
layer_range: [2, 3]
|
110 |
+
- sources:
|
111 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
112 |
+
layer_range: [2, 3]
|
113 |
+
- sources:
|
114 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
115 |
+
layer_range: [2, 3]
|
116 |
+
- sources:
|
117 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
118 |
+
layer_range: [2, 3]
|
119 |
+
- sources:
|
120 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
121 |
+
layer_range: [2, 3]
|
122 |
+
- sources:
|
123 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
124 |
+
layer_range: [2, 3]
|
125 |
+
- sources:
|
126 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
127 |
+
layer_range: [2, 3]
|
128 |
+
- sources:
|
129 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
130 |
+
layer_range: [2, 3]
|
131 |
+
|
132 |
+
# Qwen 72B Layer 2, repeated 8 times
|
133 |
+
- sources:
|
134 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
135 |
+
layer_range: [2, 3]
|
136 |
+
- sources:
|
137 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
138 |
+
layer_range: [2, 3]
|
139 |
+
- sources:
|
140 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
141 |
+
layer_range: [2, 3]
|
142 |
+
- sources:
|
143 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
144 |
+
layer_range: [2, 3]
|
145 |
+
- sources:
|
146 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
147 |
+
layer_range: [2, 3]
|
148 |
+
- sources:
|
149 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
150 |
+
layer_range: [2, 3]
|
151 |
+
- sources:
|
152 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
153 |
+
layer_range: [2, 3]
|
154 |
+
- sources:
|
155 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
156 |
+
layer_range: [2, 3]
|
157 |
+
|
158 |
+
# Replete-AI Layer 3, repeated 8 times
|
159 |
+
- sources:
|
160 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
161 |
+
layer_range: [3, 4]
|
162 |
+
- sources:
|
163 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
164 |
+
layer_range: [3, 4]
|
165 |
+
- sources:
|
166 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
167 |
+
layer_range: [3, 4]
|
168 |
+
- sources:
|
169 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
170 |
+
layer_range: [3, 4]
|
171 |
+
- sources:
|
172 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
173 |
+
layer_range: [3, 4]
|
174 |
+
- sources:
|
175 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
176 |
+
layer_range: [3, 4]
|
177 |
+
- sources:
|
178 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
179 |
+
layer_range: [3, 4]
|
180 |
+
- sources:
|
181 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
182 |
+
layer_range: [3, 4]
|
183 |
+
|
184 |
+
# Qwen 72B Layer 3, repeated 8 times
|
185 |
+
- sources:
|
186 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
187 |
+
layer_range: [3, 4]
|
188 |
+
- sources:
|
189 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
190 |
+
layer_range: [3, 4]
|
191 |
+
- sources:
|
192 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
193 |
+
layer_range: [3, 4]
|
194 |
+
- sources:
|
195 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
196 |
+
layer_range: [3, 4]
|
197 |
+
- sources:
|
198 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
199 |
+
layer_range: [3, 4]
|
200 |
+
- sources:
|
201 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
202 |
+
layer_range: [3, 4]
|
203 |
+
- sources:
|
204 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
205 |
+
layer_range: [3, 4]
|
206 |
+
- sources:
|
207 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
208 |
+
layer_range: [3, 4]
|
209 |
+
|
210 |
+
# Replete-AI Layer 4, repeated 8 times
|
211 |
+
- sources:
|
212 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
213 |
+
layer_range: [4, 5]
|
214 |
+
- sources:
|
215 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
216 |
+
layer_range: [4, 5]
|
217 |
+
- sources:
|
218 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
219 |
+
layer_range: [4, 5]
|
220 |
+
- sources:
|
221 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
222 |
+
layer_range: [4, 5]
|
223 |
+
- sources:
|
224 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
225 |
+
layer_range: [4, 5]
|
226 |
+
- sources:
|
227 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
228 |
+
layer_range: [4, 5]
|
229 |
+
- sources:
|
230 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
231 |
+
layer_range: [4, 5]
|
232 |
+
- sources:
|
233 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
234 |
+
layer_range: [4, 5]
|
235 |
+
|
236 |
+
# Qwen 72B Layer 4, repeated 8 times
|
237 |
+
- sources:
|
238 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
239 |
+
layer_range: [4, 5]
|
240 |
+
- sources:
|
241 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
242 |
+
layer_range: [4, 5]
|
243 |
+
- sources:
|
244 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
245 |
+
layer_range: [4, 5]
|
246 |
+
- sources:
|
247 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
248 |
+
layer_range: [4, 5]
|
249 |
+
- sources:
|
250 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
251 |
+
layer_range: [4, 5]
|
252 |
+
- sources:
|
253 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
254 |
+
layer_range: [4, 5]
|
255 |
+
- sources:
|
256 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
257 |
+
layer_range: [4, 5]
|
258 |
+
- sources:
|
259 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
260 |
+
layer_range: [4, 5]
|
261 |
+
|
262 |
+
# Replete-AI Layer 5, repeated 8 times
|
263 |
+
- sources:
|
264 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
265 |
+
layer_range: [5, 6]
|
266 |
+
- sources:
|
267 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
268 |
+
layer_range: [5, 6]
|
269 |
+
- sources:
|
270 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
271 |
+
layer_range: [5, 6]
|
272 |
+
- sources:
|
273 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
274 |
+
layer_range: [5, 6]
|
275 |
+
- sources:
|
276 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
277 |
+
layer_range: [5, 6]
|
278 |
+
- sources:
|
279 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
280 |
+
layer_range: [5, 6]
|
281 |
+
- sources:
|
282 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
283 |
+
layer_range: [5, 6]
|
284 |
+
- sources:
|
285 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
286 |
+
layer_range: [5, 6]
|
287 |
+
|
288 |
+
# Qwen 72B Layer 5, repeated 8 times
|
289 |
+
- sources:
|
290 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
291 |
+
layer_range: [5, 6]
|
292 |
+
- sources:
|
293 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
294 |
+
layer_range: [5, 6]
|
295 |
+
- sources:
|
296 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
297 |
+
layer_range: [5, 6]
|
298 |
+
- sources:
|
299 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
300 |
+
layer_range: [5, 6]
|
301 |
+
- sources:
|
302 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
303 |
+
layer_range: [5, 6]
|
304 |
+
- sources:
|
305 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
306 |
+
layer_range: [5, 6]
|
307 |
+
- sources:
|
308 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
309 |
+
layer_range: [5, 6]
|
310 |
+
- sources:
|
311 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
312 |
+
layer_range: [5, 6]
|
313 |
+
|
314 |
+
# Replete-AI Layer 6, repeated 8 times
|
315 |
+
- sources:
|
316 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
317 |
+
layer_range: [6, 7]
|
318 |
+
- sources:
|
319 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
320 |
+
layer_range: [6, 7]
|
321 |
+
- sources:
|
322 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
323 |
+
layer_range: [6, 7]
|
324 |
+
- sources:
|
325 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
326 |
+
layer_range: [6, 7]
|
327 |
+
- sources:
|
328 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
329 |
+
layer_range: [6, 7]
|
330 |
+
- sources:
|
331 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
332 |
+
layer_range: [6, 7]
|
333 |
+
- sources:
|
334 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
335 |
+
layer_range: [6, 7]
|
336 |
+
- sources:
|
337 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
338 |
+
layer_range: [6, 7]
|
339 |
+
|
340 |
+
# Qwen 72B Layer 6, repeated 8 times
|
341 |
+
- sources:
|
342 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
343 |
+
layer_range: [6, 7]
|
344 |
+
- sources:
|
345 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
346 |
+
layer_range: [6, 7]
|
347 |
+
- sources:
|
348 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
349 |
+
layer_range: [6, 7]
|
350 |
+
- sources:
|
351 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
352 |
+
layer_range: [6, 7]
|
353 |
+
- sources:
|
354 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
355 |
+
layer_range: [6, 7]
|
356 |
+
- sources:
|
357 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
358 |
+
layer_range: [6, 7]
|
359 |
+
- sources:
|
360 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
361 |
+
layer_range: [6, 7]
|
362 |
+
- sources:
|
363 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
364 |
+
layer_range: [6, 7]
|
365 |
+
|
366 |
+
# Replete-AI Layer 7, repeated 8 times
|
367 |
+
- sources:
|
368 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
369 |
+
layer_range: [7, 8]
|
370 |
+
- sources:
|
371 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
372 |
+
layer_range: [7, 8]
|
373 |
+
- sources:
|
374 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
375 |
+
layer_range: [7, 8]
|
376 |
+
- sources:
|
377 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
378 |
+
layer_range: [7, 8]
|
379 |
+
- sources:
|
380 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
381 |
+
layer_range: [7, 8]
|
382 |
+
- sources:
|
383 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
384 |
+
layer_range: [7, 8]
|
385 |
+
- sources:
|
386 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
387 |
+
layer_range: [7, 8]
|
388 |
+
- sources:
|
389 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
390 |
+
layer_range: [7, 8]
|
391 |
+
|
392 |
+
# Qwen 72B Layer 7, repeated 8 times
|
393 |
+
- sources:
|
394 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
395 |
+
layer_range: [7, 8]
|
396 |
+
- sources:
|
397 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
398 |
+
layer_range: [7, 8]
|
399 |
+
- sources:
|
400 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
401 |
+
layer_range: [7, 8]
|
402 |
+
- sources:
|
403 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
404 |
+
layer_range: [7, 8]
|
405 |
+
- sources:
|
406 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
407 |
+
layer_range: [7, 8]
|
408 |
+
- sources:
|
409 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
410 |
+
layer_range: [7, 8]
|
411 |
+
- sources:
|
412 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
413 |
+
layer_range: [7, 8]
|
414 |
+
- sources:
|
415 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
416 |
+
layer_range: [7, 8]
|
417 |
+
|
418 |
+
# Replete-AI Layer 8, repeated 8 times
|
419 |
+
- sources:
|
420 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
421 |
+
layer_range: [8, 9]
|
422 |
+
- sources:
|
423 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
424 |
+
layer_range: [8, 9]
|
425 |
+
- sources:
|
426 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
427 |
+
layer_range: [8, 9]
|
428 |
+
- sources:
|
429 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
430 |
+
layer_range: [8, 9]
|
431 |
+
- sources:
|
432 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
433 |
+
layer_range: [8, 9]
|
434 |
+
- sources:
|
435 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
436 |
+
layer_range: [8, 9]
|
437 |
+
- sources:
|
438 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
439 |
+
layer_range: [8, 9]
|
440 |
+
- sources:
|
441 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
442 |
+
layer_range: [8, 9]
|
443 |
+
|
444 |
+
# Qwen 72B Layer 8, repeated 8 times
|
445 |
+
- sources:
|
446 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
447 |
+
layer_range: [8, 9]
|
448 |
+
- sources:
|
449 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
450 |
+
layer_range: [8, 9]
|
451 |
+
- sources:
|
452 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
453 |
+
layer_range: [8, 9]
|
454 |
+
- sources:
|
455 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
456 |
+
layer_range: [8, 9]
|
457 |
+
- sources:
|
458 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
459 |
+
layer_range: [8, 9]
|
460 |
+
- sources:
|
461 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
462 |
+
layer_range: [8, 9]
|
463 |
+
- sources:
|
464 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
465 |
+
layer_range: [8, 9]
|
466 |
+
- sources:
|
467 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
468 |
+
layer_range: [8, 9]
|
469 |
+
|
470 |
+
# Replete-AI Layer 9, repeated 8 times
|
471 |
+
- sources:
|
472 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
473 |
+
layer_range: [9, 10]
|
474 |
+
- sources:
|
475 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
476 |
+
layer_range: [9, 10]
|
477 |
+
- sources:
|
478 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
479 |
+
layer_range: [9, 10]
|
480 |
+
- sources:
|
481 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
482 |
+
layer_range: [9, 10]
|
483 |
+
- sources:
|
484 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
485 |
+
layer_range: [9, 10]
|
486 |
+
- sources:
|
487 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
488 |
+
layer_range: [9, 10]
|
489 |
+
- sources:
|
490 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
491 |
+
layer_range: [9, 10]
|
492 |
+
- sources:
|
493 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
494 |
+
layer_range: [9, 10]
|
495 |
+
|
496 |
+
# Qwen 72B Layer 9, repeated 8 times
|
497 |
+
- sources:
|
498 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
499 |
+
layer_range: [9, 10]
|
500 |
+
- sources:
|
501 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
502 |
+
layer_range: [9, 10]
|
503 |
+
- sources:
|
504 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
505 |
+
layer_range: [9, 10]
|
506 |
+
- sources:
|
507 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
508 |
+
layer_range: [9, 10]
|
509 |
+
- sources:
|
510 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
511 |
+
layer_range: [9, 10]
|
512 |
+
- sources:
|
513 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
514 |
+
layer_range: [9, 10]
|
515 |
+
- sources:
|
516 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
517 |
+
layer_range: [9, 10]
|
518 |
+
- sources:
|
519 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
520 |
+
layer_range: [9, 10]
|
521 |
+
|
522 |
+
# Replete-AI Layer 10, repeated 8 times
|
523 |
+
- sources:
|
524 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
525 |
+
layer_range: [10, 11]
|
526 |
+
- sources:
|
527 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
528 |
+
layer_range: [10, 11]
|
529 |
+
- sources:
|
530 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
531 |
+
layer_range: [10, 11]
|
532 |
+
- sources:
|
533 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
534 |
+
layer_range: [10, 11]
|
535 |
+
- sources:
|
536 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
537 |
+
layer_range: [10, 11]
|
538 |
+
- sources:
|
539 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
540 |
+
layer_range: [10, 11]
|
541 |
+
- sources:
|
542 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
543 |
+
layer_range: [10, 11]
|
544 |
+
- sources:
|
545 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
546 |
+
layer_range: [10, 11]
|
547 |
+
|
548 |
+
# Qwen 72B Layer 10, repeated 8 times
|
549 |
+
- sources:
|
550 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
551 |
+
layer_range: [10, 11]
|
552 |
+
- sources:
|
553 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
554 |
+
layer_range: [10, 11]
|
555 |
+
- sources:
|
556 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
557 |
+
layer_range: [10, 11]
|
558 |
+
- sources:
|
559 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
560 |
+
layer_range: [10, 11]
|
561 |
+
- sources:
|
562 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
563 |
+
layer_range: [10, 11]
|
564 |
+
- sources:
|
565 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
566 |
+
layer_range: [10, 11]
|
567 |
+
- sources:
|
568 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
569 |
+
layer_range: [10, 11]
|
570 |
+
- sources:
|
571 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
572 |
+
layer_range: [10, 11]
|
573 |
+
|
574 |
+
# Replete-AI Layer 11, repeated 8 times
|
575 |
+
- sources:
|
576 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
577 |
+
layer_range: [11, 12]
|
578 |
+
- sources:
|
579 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
580 |
+
layer_range: [11, 12]
|
581 |
+
- sources:
|
582 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
583 |
+
layer_range: [11, 12]
|
584 |
+
- sources:
|
585 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
586 |
+
layer_range: [11, 12]
|
587 |
+
- sources:
|
588 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
589 |
+
layer_range: [11, 12]
|
590 |
+
- sources:
|
591 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
592 |
+
layer_range: [11, 12]
|
593 |
+
- sources:
|
594 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
595 |
+
layer_range: [11, 12]
|
596 |
+
- sources:
|
597 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
598 |
+
layer_range: [11, 12]
|
599 |
+
|
600 |
+
# Qwen 72B Layer 11, repeated 8 times
|
601 |
+
- sources:
|
602 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
603 |
+
layer_range: [11, 12]
|
604 |
+
- sources:
|
605 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
606 |
+
layer_range: [11, 12]
|
607 |
+
- sources:
|
608 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
609 |
+
layer_range: [11, 12]
|
610 |
+
- sources:
|
611 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
612 |
+
layer_range: [11, 12]
|
613 |
+
- sources:
|
614 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
615 |
+
layer_range: [11, 12]
|
616 |
+
- sources:
|
617 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
618 |
+
layer_range: [11, 12]
|
619 |
+
- sources:
|
620 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
621 |
+
layer_range: [11, 12]
|
622 |
+
- sources:
|
623 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
624 |
+
layer_range: [11, 12]
|
625 |
+
|
626 |
+
# Replete-AI Layer 12, repeated 8 times
|
627 |
+
- sources:
|
628 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
629 |
+
layer_range: [12, 13]
|
630 |
+
- sources:
|
631 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
632 |
+
layer_range: [12, 13]
|
633 |
+
- sources:
|
634 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
635 |
+
layer_range: [12, 13]
|
636 |
+
- sources:
|
637 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
638 |
+
layer_range: [12, 13]
|
639 |
+
- sources:
|
640 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
641 |
+
layer_range: [12, 13]
|
642 |
+
- sources:
|
643 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
644 |
+
layer_range: [12, 13]
|
645 |
+
- sources:
|
646 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
647 |
+
layer_range: [12, 13]
|
648 |
+
- sources:
|
649 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
650 |
+
layer_range: [12, 13]
|
651 |
+
|
652 |
+
# Qwen 72B Layer 12, repeated 8 times
|
653 |
+
- sources:
|
654 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
655 |
+
layer_range: [12, 13]
|
656 |
+
- sources:
|
657 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
658 |
+
layer_range: [12, 13]
|
659 |
+
- sources:
|
660 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
661 |
+
layer_range: [12, 13]
|
662 |
+
- sources:
|
663 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
664 |
+
layer_range: [12, 13]
|
665 |
+
- sources:
|
666 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
667 |
+
layer_range: [12, 13]
|
668 |
+
- sources:
|
669 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
670 |
+
layer_range: [12, 13]
|
671 |
+
- sources:
|
672 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
673 |
+
layer_range: [12, 13]
|
674 |
+
- sources:
|
675 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
676 |
+
layer_range: [12, 13]
|
677 |
+
|
678 |
+
# Replete-AI Layer 13, repeated 8 times
|
679 |
+
- sources:
|
680 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
681 |
+
layer_range: [13, 14]
|
682 |
+
- sources:
|
683 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
684 |
+
layer_range: [13, 14]
|
685 |
+
- sources:
|
686 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
687 |
+
layer_range: [13, 14]
|
688 |
+
- sources:
|
689 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
690 |
+
layer_range: [13, 14]
|
691 |
+
- sources:
|
692 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
693 |
+
layer_range: [13, 14]
|
694 |
+
- sources:
|
695 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
696 |
+
layer_range: [13, 14]
|
697 |
+
- sources:
|
698 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
699 |
+
layer_range: [13, 14]
|
700 |
+
- sources:
|
701 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
702 |
+
layer_range: [13, 14]
|
703 |
+
|
704 |
+
# Qwen 72B Layer 13, repeated 8 times
|
705 |
+
- sources:
|
706 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
707 |
+
layer_range: [13, 14]
|
708 |
+
- sources:
|
709 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
710 |
+
layer_range: [13, 14]
|
711 |
+
- sources:
|
712 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
713 |
+
layer_range: [13, 14]
|
714 |
+
- sources:
|
715 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
716 |
+
layer_range: [13, 14]
|
717 |
+
- sources:
|
718 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
719 |
+
layer_range: [13, 14]
|
720 |
+
- sources:
|
721 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
722 |
+
layer_range: [13, 14]
|
723 |
+
- sources:
|
724 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
725 |
+
layer_range: [13, 14]
|
726 |
+
- sources:
|
727 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
728 |
+
layer_range: [13, 14]
|
729 |
+
|
730 |
+
# Replete-AI Layer 14, repeated 8 times
|
731 |
+
- sources:
|
732 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
733 |
+
layer_range: [14, 15]
|
734 |
+
- sources:
|
735 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
736 |
+
layer_range: [14, 15]
|
737 |
+
- sources:
|
738 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
739 |
+
layer_range: [14, 15]
|
740 |
+
- sources:
|
741 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
742 |
+
layer_range: [14, 15]
|
743 |
+
- sources:
|
744 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
745 |
+
layer_range: [14, 15]
|
746 |
+
- sources:
|
747 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
748 |
+
layer_range: [14, 15]
|
749 |
+
- sources:
|
750 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
751 |
+
layer_range: [14, 15]
|
752 |
+
- sources:
|
753 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
754 |
+
layer_range: [14, 15]
|
755 |
+
|
756 |
+
# Qwen 72B Layer 14, repeated 8 times
|
757 |
+
- sources:
|
758 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
759 |
+
layer_range: [14, 15]
|
760 |
+
- sources:
|
761 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
762 |
+
layer_range: [14, 15]
|
763 |
+
- sources:
|
764 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
765 |
+
layer_range: [14, 15]
|
766 |
+
- sources:
|
767 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
768 |
+
layer_range: [14, 15]
|
769 |
+
- sources:
|
770 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
771 |
+
layer_range: [14, 15]
|
772 |
+
- sources:
|
773 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
774 |
+
layer_range: [14, 15]
|
775 |
+
- sources:
|
776 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
777 |
+
layer_range: [14, 15]
|
778 |
+
- sources:
|
779 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
780 |
+
layer_range: [14, 15]
|
781 |
+
|
782 |
+
# Replete-AI Layer 15, repeated 8 times
|
783 |
+
- sources:
|
784 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
785 |
+
layer_range: [15, 16]
|
786 |
+
- sources:
|
787 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
788 |
+
layer_range: [15, 16]
|
789 |
+
- sources:
|
790 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
791 |
+
layer_range: [15, 16]
|
792 |
+
- sources:
|
793 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
794 |
+
layer_range: [15, 16]
|
795 |
+
- sources:
|
796 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
797 |
+
layer_range: [15, 16]
|
798 |
+
- sources:
|
799 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
800 |
+
layer_range: [15, 16]
|
801 |
+
- sources:
|
802 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
803 |
+
layer_range: [15, 16]
|
804 |
+
- sources:
|
805 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
806 |
+
layer_range: [15, 16]
|
807 |
+
|
808 |
+
# Qwen 72B Layer 15, repeated 8 times
|
809 |
+
- sources:
|
810 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
811 |
+
layer_range: [15, 16]
|
812 |
+
- sources:
|
813 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
814 |
+
layer_range: [15, 16]
|
815 |
+
- sources:
|
816 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
817 |
+
layer_range: [15, 16]
|
818 |
+
- sources:
|
819 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
820 |
+
layer_range: [15, 16]
|
821 |
+
- sources:
|
822 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
823 |
+
layer_range: [15, 16]
|
824 |
+
- sources:
|
825 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
826 |
+
layer_range: [15, 16]
|
827 |
+
- sources:
|
828 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
829 |
+
layer_range: [15, 16]
|
830 |
+
- sources:
|
831 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
832 |
+
layer_range: [15, 16]
|
833 |
+
|
834 |
+
# Replete-AI Layer 16, repeated 8 times
|
835 |
+
- sources:
|
836 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
837 |
+
layer_range: [16, 17]
|
838 |
+
- sources:
|
839 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
840 |
+
layer_range: [16, 17]
|
841 |
+
- sources:
|
842 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
843 |
+
layer_range: [16, 17]
|
844 |
+
- sources:
|
845 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
846 |
+
layer_range: [16, 17]
|
847 |
+
- sources:
|
848 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
849 |
+
layer_range: [16, 17]
|
850 |
+
- sources:
|
851 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
852 |
+
layer_range: [16, 17]
|
853 |
+
- sources:
|
854 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
855 |
+
layer_range: [16, 17]
|
856 |
+
- sources:
|
857 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
858 |
+
layer_range: [16, 17]
|
859 |
+
|
860 |
+
# Qwen 72B Layer 16, repeated 8 times
|
861 |
+
- sources:
|
862 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
863 |
+
layer_range: [16, 17]
|
864 |
+
- sources:
|
865 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
866 |
+
layer_range: [16, 17]
|
867 |
+
- sources:
|
868 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
869 |
+
layer_range: [16, 17]
|
870 |
+
- sources:
|
871 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
872 |
+
layer_range: [16, 17]
|
873 |
+
- sources:
|
874 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
875 |
+
layer_range: [16, 17]
|
876 |
+
- sources:
|
877 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
878 |
+
layer_range: [16, 17]
|
879 |
+
- sources:
|
880 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
881 |
+
layer_range: [16, 17]
|
882 |
+
- sources:
|
883 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
884 |
+
layer_range: [16, 17]
|
885 |
+
|
886 |
+
# Replete-AI Layer 17, repeated 8 times
|
887 |
+
- sources:
|
888 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
889 |
+
layer_range: [17, 18]
|
890 |
+
- sources:
|
891 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
892 |
+
layer_range: [17, 18]
|
893 |
+
- sources:
|
894 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
895 |
+
layer_range: [17, 18]
|
896 |
+
- sources:
|
897 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
898 |
+
layer_range: [17, 18]
|
899 |
+
- sources:
|
900 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
901 |
+
layer_range: [17, 18]
|
902 |
+
- sources:
|
903 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
904 |
+
layer_range: [17, 18]
|
905 |
+
- sources:
|
906 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
907 |
+
layer_range: [17, 18]
|
908 |
+
- sources:
|
909 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
910 |
+
layer_range: [17, 18]
|
911 |
+
|
912 |
+
# Qwen 72B Layer 17, repeated 8 times
|
913 |
+
- sources:
|
914 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
915 |
+
layer_range: [17, 18]
|
916 |
+
- sources:
|
917 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
918 |
+
layer_range: [17, 18]
|
919 |
+
- sources:
|
920 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
921 |
+
layer_range: [17, 18]
|
922 |
+
- sources:
|
923 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
924 |
+
layer_range: [17, 18]
|
925 |
+
- sources:
|
926 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
927 |
+
layer_range: [17, 18]
|
928 |
+
- sources:
|
929 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
930 |
+
layer_range: [17, 18]
|
931 |
+
- sources:
|
932 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
933 |
+
layer_range: [17, 18]
|
934 |
+
- sources:
|
935 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
936 |
+
layer_range: [17, 18]
|
937 |
+
|
938 |
+
# Replete-AI Layer 18, repeated 8 times
|
939 |
+
- sources:
|
940 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
941 |
+
layer_range: [18, 19]
|
942 |
+
- sources:
|
943 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
944 |
+
layer_range: [18, 19]
|
945 |
+
- sources:
|
946 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
947 |
+
layer_range: [18, 19]
|
948 |
+
- sources:
|
949 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
950 |
+
layer_range: [18, 19]
|
951 |
+
- sources:
|
952 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
953 |
+
layer_range: [18, 19]
|
954 |
+
- sources:
|
955 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
956 |
+
layer_range: [18, 19]
|
957 |
+
- sources:
|
958 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
959 |
+
layer_range: [18, 19]
|
960 |
+
- sources:
|
961 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
962 |
+
layer_range: [18, 19]
|
963 |
+
|
964 |
+
# Qwen 72B Layer 18, repeated 8 times
|
965 |
+
- sources:
|
966 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
967 |
+
layer_range: [18, 19]
|
968 |
+
- sources:
|
969 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
970 |
+
layer_range: [18, 19]
|
971 |
+
- sources:
|
972 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
973 |
+
layer_range: [18, 19]
|
974 |
+
- sources:
|
975 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
976 |
+
layer_range: [18, 19]
|
977 |
+
- sources:
|
978 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
979 |
+
layer_range: [18, 19]
|
980 |
+
- sources:
|
981 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
982 |
+
layer_range: [18, 19]
|
983 |
+
- sources:
|
984 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
985 |
+
layer_range: [18, 19]
|
986 |
+
- sources:
|
987 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
988 |
+
layer_range: [18, 19]
|
989 |
+
|
990 |
+
# Replete-AI Layer 19, repeated 8 times
|
991 |
+
- sources:
|
992 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
993 |
+
layer_range: [19, 20]
|
994 |
+
- sources:
|
995 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
996 |
+
layer_range: [19, 20]
|
997 |
+
- sources:
|
998 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
999 |
+
layer_range: [19, 20]
|
1000 |
+
- sources:
|
1001 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1002 |
+
layer_range: [19, 20]
|
1003 |
+
- sources:
|
1004 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1005 |
+
layer_range: [19, 20]
|
1006 |
+
- sources:
|
1007 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1008 |
+
layer_range: [19, 20]
|
1009 |
+
- sources:
|
1010 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1011 |
+
layer_range: [19, 20]
|
1012 |
+
- sources:
|
1013 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1014 |
+
layer_range: [19, 20]
|
1015 |
+
|
1016 |
+
# Qwen 72B Layer 19, repeated 8 times
|
1017 |
+
- sources:
|
1018 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1019 |
+
layer_range: [19, 20]
|
1020 |
+
- sources:
|
1021 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1022 |
+
layer_range: [19, 20]
|
1023 |
+
- sources:
|
1024 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1025 |
+
layer_range: [19, 20]
|
1026 |
+
- sources:
|
1027 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1028 |
+
layer_range: [19, 20]
|
1029 |
+
- sources:
|
1030 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1031 |
+
layer_range: [19, 20]
|
1032 |
+
- sources:
|
1033 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1034 |
+
layer_range: [19, 20]
|
1035 |
+
- sources:
|
1036 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1037 |
+
layer_range: [19, 20]
|
1038 |
+
- sources:
|
1039 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1040 |
+
layer_range: [19, 20]
|
1041 |
+
|
1042 |
+
# Replete-AI Layer 20, repeated 8 times
|
1043 |
+
- sources:
|
1044 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1045 |
+
layer_range: [20, 21]
|
1046 |
+
- sources:
|
1047 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1048 |
+
layer_range: [20, 21]
|
1049 |
+
- sources:
|
1050 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1051 |
+
layer_range: [20, 21]
|
1052 |
+
- sources:
|
1053 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1054 |
+
layer_range: [20, 21]
|
1055 |
+
- sources:
|
1056 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1057 |
+
layer_range: [20, 21]
|
1058 |
+
- sources:
|
1059 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1060 |
+
layer_range: [20, 21]
|
1061 |
+
- sources:
|
1062 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1063 |
+
layer_range: [20, 21]
|
1064 |
+
- sources:
|
1065 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1066 |
+
layer_range: [20, 21]
|
1067 |
+
|
1068 |
+
# Qwen 72B Layer 20, repeated 8 times
|
1069 |
+
- sources:
|
1070 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1071 |
+
layer_range: [20, 21]
|
1072 |
+
- sources:
|
1073 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1074 |
+
layer_range: [20, 21]
|
1075 |
+
- sources:
|
1076 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1077 |
+
layer_range: [20, 21]
|
1078 |
+
- sources:
|
1079 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1080 |
+
layer_range: [20, 21]
|
1081 |
+
- sources:
|
1082 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1083 |
+
layer_range: [20, 21]
|
1084 |
+
- sources:
|
1085 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1086 |
+
layer_range: [20, 21]
|
1087 |
+
- sources:
|
1088 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1089 |
+
layer_range: [20, 21]
|
1090 |
+
- sources:
|
1091 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1092 |
+
layer_range: [20, 21]
|
1093 |
+
|
1094 |
+
# Replete-AI Layer 21, repeated 8 times
|
1095 |
+
- sources:
|
1096 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1097 |
+
layer_range: [21, 22]
|
1098 |
+
- sources:
|
1099 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1100 |
+
layer_range: [21, 22]
|
1101 |
+
- sources:
|
1102 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1103 |
+
layer_range: [21, 22]
|
1104 |
+
- sources:
|
1105 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1106 |
+
layer_range: [21, 22]
|
1107 |
+
- sources:
|
1108 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1109 |
+
layer_range: [21, 22]
|
1110 |
+
- sources:
|
1111 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1112 |
+
layer_range: [21, 22]
|
1113 |
+
- sources:
|
1114 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1115 |
+
layer_range: [21, 22]
|
1116 |
+
- sources:
|
1117 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1118 |
+
layer_range: [21, 22]
|
1119 |
+
|
1120 |
+
# Qwen 72B Layer 21, repeated 8 times
|
1121 |
+
- sources:
|
1122 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1123 |
+
layer_range: [21, 22]
|
1124 |
+
- sources:
|
1125 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1126 |
+
layer_range: [21, 22]
|
1127 |
+
- sources:
|
1128 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1129 |
+
layer_range: [21, 22]
|
1130 |
+
- sources:
|
1131 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1132 |
+
layer_range: [21, 22]
|
1133 |
+
- sources:
|
1134 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1135 |
+
layer_range: [21, 22]
|
1136 |
+
- sources:
|
1137 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1138 |
+
layer_range: [21, 22]
|
1139 |
+
- sources:
|
1140 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1141 |
+
layer_range: [21, 22]
|
1142 |
+
- sources:
|
1143 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1144 |
+
layer_range: [21, 22]
|
1145 |
+
|
1146 |
+
# Replete-AI Layer 22, repeated 8 times
|
1147 |
+
- sources:
|
1148 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1149 |
+
layer_range: [22, 23]
|
1150 |
+
- sources:
|
1151 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1152 |
+
layer_range: [22, 23]
|
1153 |
+
- sources:
|
1154 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1155 |
+
layer_range: [22, 23]
|
1156 |
+
- sources:
|
1157 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1158 |
+
layer_range: [22, 23]
|
1159 |
+
- sources:
|
1160 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1161 |
+
layer_range: [22, 23]
|
1162 |
+
- sources:
|
1163 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1164 |
+
layer_range: [22, 23]
|
1165 |
+
- sources:
|
1166 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1167 |
+
layer_range: [22, 23]
|
1168 |
+
- sources:
|
1169 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1170 |
+
layer_range: [22, 23]
|
1171 |
+
|
1172 |
+
# Qwen 72B Layer 22, repeated 8 times
|
1173 |
+
- sources:
|
1174 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1175 |
+
layer_range: [22, 23]
|
1176 |
+
- sources:
|
1177 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1178 |
+
layer_range: [22, 23]
|
1179 |
+
- sources:
|
1180 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1181 |
+
layer_range: [22, 23]
|
1182 |
+
- sources:
|
1183 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1184 |
+
layer_range: [22, 23]
|
1185 |
+
- sources:
|
1186 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1187 |
+
layer_range: [22, 23]
|
1188 |
+
- sources:
|
1189 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1190 |
+
layer_range: [22, 23]
|
1191 |
+
- sources:
|
1192 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1193 |
+
layer_range: [22, 23]
|
1194 |
+
- sources:
|
1195 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1196 |
+
layer_range: [22, 23]
|
1197 |
+
|
1198 |
+
# Replete-AI Layer 23, repeated 8 times
|
1199 |
+
- sources:
|
1200 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1201 |
+
layer_range: [23, 24]
|
1202 |
+
- sources:
|
1203 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1204 |
+
layer_range: [23, 24]
|
1205 |
+
- sources:
|
1206 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1207 |
+
layer_range: [23, 24]
|
1208 |
+
- sources:
|
1209 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1210 |
+
layer_range: [23, 24]
|
1211 |
+
- sources:
|
1212 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1213 |
+
layer_range: [23, 24]
|
1214 |
+
- sources:
|
1215 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1216 |
+
layer_range: [23, 24]
|
1217 |
+
- sources:
|
1218 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1219 |
+
layer_range: [23, 24]
|
1220 |
+
- sources:
|
1221 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1222 |
+
layer_range: [23, 24]
|
1223 |
+
|
1224 |
+
# Qwen 72B Layer 23, repeated 8 times
|
1225 |
+
- sources:
|
1226 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1227 |
+
layer_range: [23, 24]
|
1228 |
+
- sources:
|
1229 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1230 |
+
layer_range: [23, 24]
|
1231 |
+
- sources:
|
1232 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1233 |
+
layer_range: [23, 24]
|
1234 |
+
- sources:
|
1235 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1236 |
+
layer_range: [23, 24]
|
1237 |
+
- sources:
|
1238 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1239 |
+
layer_range: [23, 24]
|
1240 |
+
- sources:
|
1241 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1242 |
+
layer_range: [23, 24]
|
1243 |
+
- sources:
|
1244 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1245 |
+
layer_range: [23, 24]
|
1246 |
+
- sources:
|
1247 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1248 |
+
layer_range: [23, 24]
|
1249 |
+
|
1250 |
+
# Replete-AI Layer 24, repeated 8 times
|
1251 |
+
- sources:
|
1252 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1253 |
+
layer_range: [24, 25]
|
1254 |
+
- sources:
|
1255 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1256 |
+
layer_range: [24, 25]
|
1257 |
+
- sources:
|
1258 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1259 |
+
layer_range: [24, 25]
|
1260 |
+
- sources:
|
1261 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1262 |
+
layer_range: [24, 25]
|
1263 |
+
- sources:
|
1264 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1265 |
+
layer_range: [24, 25]
|
1266 |
+
- sources:
|
1267 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1268 |
+
layer_range: [24, 25]
|
1269 |
+
- sources:
|
1270 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1271 |
+
layer_range: [24, 25]
|
1272 |
+
- sources:
|
1273 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1274 |
+
layer_range: [24, 25]
|
1275 |
+
|
1276 |
+
# Qwen 72B Layer 24, repeated 8 times
|
1277 |
+
- sources:
|
1278 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1279 |
+
layer_range: [24, 25]
|
1280 |
+
- sources:
|
1281 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1282 |
+
layer_range: [24, 25]
|
1283 |
+
- sources:
|
1284 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1285 |
+
layer_range: [24, 25]
|
1286 |
+
- sources:
|
1287 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1288 |
+
layer_range: [24, 25]
|
1289 |
+
- sources:
|
1290 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1291 |
+
layer_range: [24, 25]
|
1292 |
+
- sources:
|
1293 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1294 |
+
layer_range: [24, 25]
|
1295 |
+
- sources:
|
1296 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1297 |
+
layer_range: [24, 25]
|
1298 |
+
- sources:
|
1299 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1300 |
+
layer_range: [24, 25]
|
1301 |
+
|
1302 |
+
# Replete-AI Layer 25, repeated 8 times
|
1303 |
+
- sources:
|
1304 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1305 |
+
layer_range: [25, 26]
|
1306 |
+
- sources:
|
1307 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1308 |
+
layer_range: [25, 26]
|
1309 |
+
- sources:
|
1310 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1311 |
+
layer_range: [25, 26]
|
1312 |
+
- sources:
|
1313 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1314 |
+
layer_range: [25, 26]
|
1315 |
+
- sources:
|
1316 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1317 |
+
layer_range: [25, 26]
|
1318 |
+
- sources:
|
1319 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1320 |
+
layer_range: [25, 26]
|
1321 |
+
- sources:
|
1322 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1323 |
+
layer_range: [25, 26]
|
1324 |
+
- sources:
|
1325 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1326 |
+
layer_range: [25, 26]
|
1327 |
+
|
1328 |
+
# Qwen 72B Layer 25, repeated 8 times
|
1329 |
+
- sources:
|
1330 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1331 |
+
layer_range: [25, 26]
|
1332 |
+
- sources:
|
1333 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1334 |
+
layer_range: [25, 26]
|
1335 |
+
- sources:
|
1336 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1337 |
+
layer_range: [25, 26]
|
1338 |
+
- sources:
|
1339 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1340 |
+
layer_range: [25, 26]
|
1341 |
+
- sources:
|
1342 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1343 |
+
layer_range: [25, 26]
|
1344 |
+
- sources:
|
1345 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1346 |
+
layer_range: [25, 26]
|
1347 |
+
- sources:
|
1348 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1349 |
+
layer_range: [25, 26]
|
1350 |
+
- sources:
|
1351 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1352 |
+
layer_range: [25, 26]
|
1353 |
+
|
1354 |
+
# Replete-AI Layer 26, repeated 8 times
|
1355 |
+
- sources:
|
1356 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1357 |
+
layer_range: [26, 27]
|
1358 |
+
- sources:
|
1359 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1360 |
+
layer_range: [26, 27]
|
1361 |
+
- sources:
|
1362 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1363 |
+
layer_range: [26, 27]
|
1364 |
+
- sources:
|
1365 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1366 |
+
layer_range: [26, 27]
|
1367 |
+
- sources:
|
1368 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1369 |
+
layer_range: [26, 27]
|
1370 |
+
- sources:
|
1371 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1372 |
+
layer_range: [26, 27]
|
1373 |
+
- sources:
|
1374 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1375 |
+
layer_range: [26, 27]
|
1376 |
+
- sources:
|
1377 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1378 |
+
layer_range: [26, 27]
|
1379 |
+
|
1380 |
+
# Qwen 72B Layer 26, repeated 8 times
|
1381 |
+
- sources:
|
1382 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1383 |
+
layer_range: [26, 27]
|
1384 |
+
- sources:
|
1385 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1386 |
+
layer_range: [26, 27]
|
1387 |
+
- sources:
|
1388 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1389 |
+
layer_range: [26, 27]
|
1390 |
+
- sources:
|
1391 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1392 |
+
layer_range: [26, 27]
|
1393 |
+
- sources:
|
1394 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1395 |
+
layer_range: [26, 27]
|
1396 |
+
- sources:
|
1397 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1398 |
+
layer_range: [26, 27]
|
1399 |
+
- sources:
|
1400 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1401 |
+
layer_range: [26, 27]
|
1402 |
+
- sources:
|
1403 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1404 |
+
layer_range: [26, 27]
|
1405 |
+
|
1406 |
+
# Replete-AI Layer 27, repeated 8 times
|
1407 |
+
- sources:
|
1408 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1409 |
+
layer_range: [27, 28]
|
1410 |
+
- sources:
|
1411 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1412 |
+
layer_range: [27, 28]
|
1413 |
+
- sources:
|
1414 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1415 |
+
layer_range: [27, 28]
|
1416 |
+
- sources:
|
1417 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1418 |
+
layer_range: [27, 28]
|
1419 |
+
- sources:
|
1420 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1421 |
+
layer_range: [27, 28]
|
1422 |
+
- sources:
|
1423 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1424 |
+
layer_range: [27, 28]
|
1425 |
+
- sources:
|
1426 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1427 |
+
layer_range: [27, 28]
|
1428 |
+
- sources:
|
1429 |
+
- model: Replete-AI/Replete-LLM-V2.5-Qwen-7b
|
1430 |
+
layer_range: [27, 28]
|
1431 |
+
|
1432 |
+
# Qwen 72B Layer 27, repeated 8 times
|
1433 |
+
- sources:
|
1434 |
+
- model: Qwen/Qwen2.5-72B-Instruct
|
1435 |
+
layer_range: [27, 80]
|
1436 |
+
|
1437 |
+
merge_method: passthrough
|
1438 |
+
dtype: float16
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acfdb5e3f1743583aed6bcf294a600b982820ff9a2e6fa0889a86f77a3104cdd
|
3 |
+
size 4550486200
|
model-00002-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7e38eee92d642a28e2802cd7fd0004e25f11f2bb6565c1f94b521964388a028
|
3 |
+
size 4961863488
|
model-00003-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b4fc447fe65666cafae56ffe1497d47cfc53f70a9c01a0886ce5fd59050a619
|
3 |
+
size 4961863488
|
model-00004-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c4696a858b24c40fe415bd904354e15b1e459877269fa60f35e4002e8914dbc
|
3 |
+
size 4962082416
|
model-00005-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d8d7887685e90cb6a8c69bfb91494bbfba203dd91e0461ef6b5f0e65fc752d7
|
3 |
+
size 4823861800
|
model-00006-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11f5a108e0a36924106fba39d50a74f236a496443f9016755d077177668a06e1
|
3 |
+
size 4961863496
|
model-00007-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cda4c65a58cc512e8302920e9aa5e66d2249d2bf1c8d4d1841c9b8d0b6223737
|
3 |
+
size 4961863480
|
model-00008-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eba338b9a7779020cf69b46daff377158513b63911166bcad5dcb24cdcca3020
|
3 |
+
size 4941522000
|
model-00009-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:350bdd75180cfbdf83c336c96f3076da055350b8819b16bc3511c9a4f63545c9
|
3 |
+
size 4961863512
|
model-00010-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b48100cf048a90f6501cc4cea3194a8041f45d5042f43b41b8a48fedc92aeb4
|
3 |
+
size 4961863512
|
model-00011-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2630072bac92be4c63baa908004e20a822fa20eeb116b00ac6a0d35eda8926d0
|
3 |
+
size 4995634816
|
model-00012-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c5e53d95fdd0fdc9c46c93a1cd11893eba65bfd40d311f6f8f928d4ab57b122
|
3 |
+
size 4790309576
|
model-00013-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ac0047820ba63c3dd3e34f327964309840e1104265c8ed8460d5cd19f60fa95
|
3 |
+
size 4961863512
|
model-00014-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:682c43f8d01c6b0c060c927d9e49a001b25d503ef67438f4fca795f763e4ba7a
|
3 |
+
size 4961863504
|
model-00015-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe04b88b03ddf7c267783d08afaba1b447924fba90b83aa75d6bcfa2cf7bb853
|
3 |
+
size 4869999288
|
model-00016-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33a52b534625e460ac894b61bfc2887fef56733a3cc6c439661b9871917ad316
|
3 |
+
size 4915945120
|
model-00017-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7978e8562693251abb0978c2c363058ba2a6644f2bad0f26abf9a56075b359df
|
3 |
+
size 4961863512
|
model-00018-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0057948e3c7ee74144482184098a92cfae4e6d5297a1847e0f552d2d738f2d10
|
3 |
+
size 4961863496
|
model-00019-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f0eec5c5fbb3e99dcf92bab117456ad59d5bb47acafe2defcfaddcd28ea688d
|
3 |
+
size 4941522176
|
model-00020-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1dbf0927b47dcdb619fd1be5208335063b0d929d2c0e127273efc11d4382916
|
3 |
+
size 4961863512
|
model-00021-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0f504abfa87f234545cfc5219444e93c6e48d5444f099d45ac4e954c309ba44
|
3 |
+
size 4961863504
|
model-00022-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fadd1183e124284433a70cf5f9cf3cdd995c63c965ebaf561738e19c9075840d
|
3 |
+
size 4962082488
|
model-00023-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ceff64692260f1233f129e8cf1bc97e73791d02d6a7199869d7f4114cbc6304
|
3 |
+
size 4823861912
|
model-00024-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c742308b89e1df504c38979cd42f95f6cf708c68451f6ab0ca7aba4f04a5be8
|
3 |
+
size 4961863512
|
model-00025-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45a452f6761129a78ff69ac26569126c0286699b89f7ee0dbba6d966cd14a7fe
|
3 |
+
size 4961863496
|
model-00026-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ac1ef1a67956aba472645430f341ae022e5b6c624cecef2cf2d1a9d800546ca
|
3 |
+
size 4941522176
|
model-00027-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5514add6e5972cf9994c9978bdf52eff7d7c438c8a110bd4337e9f3cc01913b
|
3 |
+
size 4961863512
|
model-00028-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d70eb1854b1e63e629d72fb3e1ad3915d60b18d0d0339196b282ea9545d1de97
|
3 |
+
size 4961863512
|
model-00029-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:331b3fb68cca436961348c6825112ba78ee5958e747a81a6f859e50344b44fdb
|
3 |
+
size 4995634816
|
model-00030-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b9f5e9d8d3ec67874008e5ef4d191b345cf8290a4a9ddc1ee962536a6f4639b
|
3 |
+
size 4790309576
|
model-00031-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fd4245fc952e80b7b376ad712f7eef518a5fb8d8da937f7d02892fd7808f65d
|
3 |
+
size 4961863512
|
model-00032-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a72092996182d17ae934a8687eb90dfe0dec28aec9a2f2e6ee944d273654b004
|
3 |
+
size 4961863504
|
model-00033-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97ac923768ed471d76ccd7c63e2f0d40a6922d55e2d237a7922b90242d99dbe8
|
3 |
+
size 4869999288
|
model-00034-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e64c01d221b2f9e5d9fe2e2c6a82fa2d4dd08435ea90d89226b444d444f7a6a
|
3 |
+
size 4915945120
|
model-00035-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89985370cb8e338a6997f9808e3ee83b14e1adb08299ac822f73d09aa6159558
|
3 |
+
size 4961863512
|
model-00036-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7901de385287f496cb49c1643aacd6e33524330a1da44a74f8c789a751dd2a94
|
3 |
+
size 4961863496
|
model-00037-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07ea31bf8616338285a1509c6779e680bbcbf6bda56ea1cd6544ebdc1fd9dee8
|
3 |
+
size 4941522176
|
model-00038-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecabb3d15348c86970b05843028245a8dc1ce8e2083182aecd0753a0acc83622
|
3 |
+
size 4961863512
|
model-00039-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a4c7cd6f7440d6fdeef0de55970f9ae37d8f9f01555effa4eaa45b27b0f990b
|
3 |
+
size 4961863504
|
model-00040-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8ecea668d848dcca3a34185b1d35bcf320451b63da6b2c6eff24a2d3e9600eb
|
3 |
+
size 4962082488
|
model-00041-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50ff63c9a93bc20e18fbdaecbac3d6fbfdede3c816c8920d88dffd680767d7da
|
3 |
+
size 4823861912
|
model-00042-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0817cada018e634025d14c3b02e980d087ef1cb8ec7e5e5216c16bbeae1922b7
|
3 |
+
size 4961863512
|
model-00043-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8c0e21475a48967c10592b0dc9eb8a15b544865e779909bf85c96b501b99f00
|
3 |
+
size 4961863496
|
model-00044-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81cec7fb912cf0b88dc42c3fc2ec527945f53966af6a9d22fad96e0fe5550d2f
|
3 |
+
size 4941522160
|
model-00045-of-00119.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3148d89d2ef8d344999f0bd2eca480dc06fd15daafd6f47df30a6ff1a9e19ff
|
3 |
+
size 4961863496
|