Hugging Face's logo

BenevolenceMessiah
/
Qwen2.5-Coder-7B-Chat-Instruct-TIES

Text Generation
Transformers
Safetensors
qwen2
mergekit
Merge
conversational
text-generation-inference
Model card Files
xet
Community
BenevolenceMessiah commited on
Commit
b3b247b
·
verified ·
1 Parent(s): 6a492a2

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. README.md +5 -6
  2. mergekit_config.yml +5 -5
  3. model-00001-of-00004.safetensors +1 -1
  4. model-00002-of-00004.safetensors +1 -1
  5. model-00003-of-00004.safetensors +1 -1
  6. model-00004-of-00004.safetensors +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  base_model:
3
- - Qwen/Qwen2.5-Coder-7B
4
  - Qwen/Qwen2.5-Coder-7B-Instruct
 
5
  library_name: transformers
6
  tags:
7
  - mergekit
@@ -30,12 +30,12 @@ The following YAML configuration was used to produce this model:
30
  models:
31
  - model: Qwen/Qwen2.5-Coder-7B-Instruct
32
  parameters:
33
- density: 0.5
34
- weight: 0.5
35
  - model: Qwen/Qwen2.5-Coder-7B
36
  parameters:
37
- density: 0.5
38
- weight: 0.5
39
 
40
  merge_method: ties
41
  base_model: Qwen/Qwen2.5-Coder-7B-Instruct
@@ -44,5 +44,4 @@ parameters:
44
  int8_mask: false
45
  dtype: bfloat16
46
  tokenizer_source: union
47
-
48
  ```
 
1
  ---
2
  base_model:
 
3
  - Qwen/Qwen2.5-Coder-7B-Instruct
4
+ - Qwen/Qwen2.5-Coder-7B
5
  library_name: transformers
6
  tags:
7
  - mergekit
 
30
  models:
31
  - model: Qwen/Qwen2.5-Coder-7B-Instruct
32
  parameters:
33
+ density: 1.0
34
+ weight: 1.0
35
  - model: Qwen/Qwen2.5-Coder-7B
36
  parameters:
37
+ density: 1.0
38
+ weight: 1.0
39
 
40
  merge_method: ties
41
  base_model: Qwen/Qwen2.5-Coder-7B-Instruct
 
44
  int8_mask: false
45
  dtype: bfloat16
46
  tokenizer_source: union
 
47
  ```
mergekit_config.yml CHANGED
@@ -1,12 +1,12 @@
1
  models:
2
  - model: Qwen/Qwen2.5-Coder-7B-Instruct
3
  parameters:
4
- density: 0.5
5
- weight: 0.5
6
  - model: Qwen/Qwen2.5-Coder-7B
7
  parameters:
8
- density: 0.5
9
- weight: 0.5
10
 
11
  merge_method: ties
12
  base_model: Qwen/Qwen2.5-Coder-7B-Instruct
@@ -14,4 +14,4 @@ parameters:
14
  normalize: true
15
  int8_mask: false
16
  dtype: bfloat16
17
- tokenizer_source: union
 
1
  models:
2
  - model: Qwen/Qwen2.5-Coder-7B-Instruct
3
  parameters:
4
+ density: 1.0
5
+ weight: 1.0
6
  - model: Qwen/Qwen2.5-Coder-7B
7
  parameters:
8
+ density: 1.0
9
+ weight: 1.0
10
 
11
  merge_method: ties
12
  base_model: Qwen/Qwen2.5-Coder-7B-Instruct
 
14
  normalize: true
15
  int8_mask: false
16
  dtype: bfloat16
17
+ tokenizer_source: union
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba66af72f2239069ca41697b85d24145ecc77e74927a02215f4a6dcb1b778679
3
  size 4970978712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a880645fc66d7c85f29d9b3d9942e57d98251e8ee6cf62ab866dac59ba0bbd
3
  size 4970978712
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dd321a4073758c697e7933c83a3fe1f8027128ae652ec745099fabcd09de8e4
3
  size 4932751032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b90283c4a6f6834fabd1de389ed576e3cff6cbe58223e92b1553f5e55b259b7
3
  size 4932751032
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6db04b036f42b695e1b1db37b64c69fee8764d35b9c2dd1c629ace1d521d0dc1
3
  size 4991495808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d845e6112f843e9839d6415a7611e2c4dc91c655cce074af211671e14d3ee28
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:d22ab7f027af929bd2c86f867cdea5f7a3e913fe3f26cf961b3b2d8c3c49a7cc
3
  size 330326240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939448d68982af5c0b7d8789cd29705c7d729599407290e6ef1e1e94094ad50c
3
  size 330326240