Upload folder using huggingface_hub
Browse files- README.md +23 -10
- config.json +1 -1
- mergekit_config.yml +14 -7
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
README.md
CHANGED
@@ -1,7 +1,10 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
- bunnycore/Qwen2.5-7B-MixStock-V0.1
|
4 |
-
- bunnycore/
|
|
|
|
|
|
|
5 |
library_name: transformers
|
6 |
tags:
|
7 |
- mergekit
|
@@ -15,25 +18,35 @@ This is a merge of pre-trained language models created using [mergekit](https://
|
|
15 |
## Merge Details
|
16 |
### Merge Method
|
17 |
|
18 |
-
This model was merged using the
|
19 |
|
20 |
### Models Merged
|
21 |
|
22 |
The following models were included in the merge:
|
23 |
-
|
|
|
|
|
|
|
24 |
|
25 |
### Configuration
|
26 |
|
27 |
The following YAML configuration was used to produce this model:
|
28 |
|
29 |
```yaml
|
30 |
-
|
31 |
-
|
32 |
-
base_model: bunnycore/Qwen2.5-7B-MixStock-V0.1+bunnycore/Qwen-2.5-7b-rp-lora
|
33 |
-
dtype: bfloat16
|
34 |
-
merge_method: passthrough
|
35 |
models:
|
36 |
-
|
37 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
|
39 |
```
|
|
|
1 |
---
|
2 |
base_model:
|
3 |
- bunnycore/Qwen2.5-7B-MixStock-V0.1
|
4 |
+
- bunnycore/Qwen2.5-7B-RRP-1M
|
5 |
+
- nvidia/AceInstruct-7B
|
6 |
+
- open-r1/OpenR1-Qwen-7B
|
7 |
+
- open-thoughts/OpenThinker-7B
|
8 |
library_name: transformers
|
9 |
tags:
|
10 |
- mergekit
|
|
|
18 |
## Merge Details
|
19 |
### Merge Method
|
20 |
|
21 |
+
This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [bunnycore/Qwen2.5-7B-RRP-1M](https://huggingface.co/bunnycore/Qwen2.5-7B-RRP-1M) as a base.
|
22 |
|
23 |
### Models Merged
|
24 |
|
25 |
The following models were included in the merge:
|
26 |
+
* [bunnycore/Qwen2.5-7B-MixStock-V0.1](https://huggingface.co/bunnycore/Qwen2.5-7B-MixStock-V0.1)
|
27 |
+
* [nvidia/AceInstruct-7B](https://huggingface.co/nvidia/AceInstruct-7B)
|
28 |
+
* [open-r1/OpenR1-Qwen-7B](https://huggingface.co/open-r1/OpenR1-Qwen-7B)
|
29 |
+
* [open-thoughts/OpenThinker-7B](https://huggingface.co/open-thoughts/OpenThinker-7B)
|
30 |
|
31 |
### Configuration
|
32 |
|
33 |
The following YAML configuration was used to produce this model:
|
34 |
|
35 |
```yaml
|
|
|
|
|
|
|
|
|
|
|
36 |
models:
|
37 |
+
# Pivot model
|
38 |
+
- model: bunnycore/Qwen2.5-7B-RRP-1M
|
39 |
+
# Target models
|
40 |
+
- model: open-thoughts/OpenThinker-7B
|
41 |
+
- model: open-r1/OpenR1-Qwen-7B
|
42 |
+
- model: bunnycore/Qwen2.5-7B-MixStock-V0.1
|
43 |
+
- model: nvidia/AceInstruct-7B
|
44 |
+
merge_method: sce
|
45 |
+
base_model: bunnycore/Qwen2.5-7B-RRP-1M
|
46 |
+
parameters:
|
47 |
+
select_topk: 0.65
|
48 |
+
int8_mask: true
|
49 |
+
dtype: bfloat16
|
50 |
+
|
51 |
|
52 |
```
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "bunnycore/Qwen2.5-7B-
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bunnycore/Qwen2.5-7B-RRP-1M",
|
3 |
"architectures": [
|
4 |
"Qwen2ForCausalLM"
|
5 |
],
|
mergekit_config.yml
CHANGED
@@ -1,8 +1,15 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
base_model: bunnycore/Qwen2.5-7B-MixStock-V0.1+bunnycore/Qwen-2.5-7b-rp-lora
|
4 |
-
dtype: bfloat16
|
5 |
-
merge_method: passthrough
|
6 |
models:
|
7 |
-
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
models:
|
2 |
+
# Pivot model
|
3 |
+
- model: bunnycore/Qwen2.5-7B-RRP-1M
|
4 |
+
# Target models
|
5 |
+
- model: open-thoughts/OpenThinker-7B
|
6 |
+
- model: open-r1/OpenR1-Qwen-7B
|
7 |
+
- model: bunnycore/Qwen2.5-7B-MixStock-V0.1
|
8 |
+
- model: nvidia/AceInstruct-7B
|
9 |
+
merge_method: sce
|
10 |
+
base_model: bunnycore/Qwen2.5-7B-RRP-1M
|
11 |
+
parameters:
|
12 |
+
select_topk: 0.65
|
13 |
+
int8_mask: true
|
14 |
+
dtype: bfloat16
|
15 |
+
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4970978712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c2127c19dc89c055407464e036b94d59fc501f510f54b870c8eeb7af4603a1e
|
3 |
size 4970978712
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4932751032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:299b889e81aaf7adb0cc6a95f35d4b73c8b0a742778124cde8004e2623da3d71
|
3 |
size 4932751032
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4991495808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38c87fd618dbc84bdb83152f44d5a758f64669ff2332385ed5a0f58e6c5e49cf
|
3 |
size 4991495808
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 330326240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ab21de1801cf249039b4f14764a6b81f8e4a34cb146f14f073bb3802b4d81a0
|
3 |
size 330326240
|