Hugging Face's logo

win10
/
Qwen2.5-Math-12.3B-Instruct

Text Generation
Transformers
Safetensors
qwen2
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
win10 commited on
Commit
3de68b0
·
verified ·
1 Parent(s): 64bd8be

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. README.md +50 -0
  3. added_tokens.json +24 -0
  4. config.json +29 -0
  5. mergekit_config.yml +21 -0
  6. merges.txt +0 -0
  7. model-00001-of-00051.safetensors +3 -0
  8. model-00002-of-00051.safetensors +3 -0
  9. model-00003-of-00051.safetensors +3 -0
  10. model-00004-of-00051.safetensors +3 -0
  11. model-00005-of-00051.safetensors +3 -0
  12. model-00006-of-00051.safetensors +3 -0
  13. model-00007-of-00051.safetensors +3 -0
  14. model-00008-of-00051.safetensors +3 -0
  15. model-00009-of-00051.safetensors +3 -0
  16. model-00010-of-00051.safetensors +3 -0
  17. model-00011-of-00051.safetensors +3 -0
  18. model-00012-of-00051.safetensors +3 -0
  19. model-00013-of-00051.safetensors +3 -0
  20. model-00014-of-00051.safetensors +3 -0
  21. model-00015-of-00051.safetensors +3 -0
  22. model-00016-of-00051.safetensors +3 -0
  23. model-00017-of-00051.safetensors +3 -0
  24. model-00018-of-00051.safetensors +3 -0
  25. model-00019-of-00051.safetensors +3 -0
  26. model-00020-of-00051.safetensors +3 -0
  27. model-00021-of-00051.safetensors +3 -0
  28. model-00022-of-00051.safetensors +3 -0
  29. model-00023-of-00051.safetensors +3 -0
  30. model-00024-of-00051.safetensors +3 -0
  31. model-00025-of-00051.safetensors +3 -0
  32. model-00026-of-00051.safetensors +3 -0
  33. model-00027-of-00051.safetensors +3 -0
  34. model-00028-of-00051.safetensors +3 -0
  35. model-00029-of-00051.safetensors +3 -0
  36. model-00030-of-00051.safetensors +3 -0
  37. model-00031-of-00051.safetensors +3 -0
  38. model-00032-of-00051.safetensors +3 -0
  39. model-00033-of-00051.safetensors +3 -0
  40. model-00034-of-00051.safetensors +3 -0
  41. model-00035-of-00051.safetensors +3 -0
  42. model-00036-of-00051.safetensors +3 -0
  43. model-00037-of-00051.safetensors +3 -0
  44. model-00038-of-00051.safetensors +3 -0
  45. model-00039-of-00051.safetensors +3 -0
  46. model-00040-of-00051.safetensors +3 -0
  47. model-00041-of-00051.safetensors +3 -0
  48. model-00042-of-00051.safetensors +3 -0
  49. model-00043-of-00051.safetensors +3 -0
  50. model-00044-of-00051.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-Math-7B-Instruct
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the passthrough merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [Qwen/Qwen2.5-Math-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ dtype: bfloat16
30
+ merge_method: passthrough
31
+ slices:
32
+ - sources:
33
+ - layer_range: [0, 8]
34
+ model: Qwen/Qwen2.5-Math-7B-Instruct
35
+ - sources:
36
+ - layer_range: [4, 12]
37
+ model: Qwen/Qwen2.5-Math-7B-Instruct
38
+ - sources:
39
+ - layer_range: [8, 16]
40
+ model: Qwen/Qwen2.5-Math-7B-Instruct
41
+ - sources:
42
+ - layer_range: [12, 20]
43
+ model: Qwen/Qwen2.5-Math-7B-Instruct
44
+ - sources:
45
+ - layer_range: [16, 24]
46
+ model: Qwen/Qwen2.5-Math-7B-Instruct
47
+ - sources:
48
+ - layer_range: [20, 28]
49
+ model: Qwen/Qwen2.5-Math-7B-Instruct
50
+ ```
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 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-Math-7B-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": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 4096,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 28,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 4,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.45.2",
26
+ "use_cache": true,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 152064
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: bfloat16
2
+ merge_method: passthrough
3
+ slices:
4
+ - sources:
5
+ - layer_range: [0, 8]
6
+ model: Qwen/Qwen2.5-Math-7B-Instruct
7
+ - sources:
8
+ - layer_range: [4, 12]
9
+ model: Qwen/Qwen2.5-Math-7B-Instruct
10
+ - sources:
11
+ - layer_range: [8, 16]
12
+ model: Qwen/Qwen2.5-Math-7B-Instruct
13
+ - sources:
14
+ - layer_range: [12, 20]
15
+ model: Qwen/Qwen2.5-Math-7B-Instruct
16
+ - sources:
17
+ - layer_range: [16, 24]
18
+ model: Qwen/Qwen2.5-Math-7B-Instruct
19
+ - sources:
20
+ - layer_range: [20, 28]
21
+ model: Qwen/Qwen2.5-Math-7B-Instruct
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea48f227c229da9d43ad67ed46d339247c99cbe0149ef77758a14a81a19cc27a
3
+ size 1089994880
model-00002-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2414d668245dae5d971da53ee307d49d041ad023c90824db0f0b9b39e77305ee
3
+ size 1089994896
model-00003-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8858a7bd995dd380a89e0fc035e26f34d4c1af93fa91ac3852def52ad65084a2
3
+ size 466124232
model-00004-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e455f6fb3536017b24c75f77b3570b8a637270abab39c32341d87226bdf38f
3
+ size 466124240
model-00005-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cca71b8a5e1f2b87adf72b8d0557a75f6bab9aad631d43001f2204c7123238f9
3
+ size 407372152
model-00006-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1dc4b03d26d20bd0b9e79f05391f6a95baadf7e6b291afeaec691a7fbce0b27
3
+ size 491814488
model-00007-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6259ec72a0969539740bd546af6395cdba5b15841bb9e4bf8ef40eda9ad3fb35
3
+ size 440419456
model-00008-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:251a88461c5c1e893924acdfd5c2be6f880df3314cfcfc883a96e355fd6507ae
3
+ size 491814488
model-00009-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089c9edeabdebfdeebbd02450915adfec8549fda7ef4e94b79aa6e0039b0e1e4
3
+ size 440419448
model-00010-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d6660c9ecd9a1239fd0218c7a17e7c1a46e78e9ceba186b8fdac4a1415a9ab0
3
+ size 491814488
model-00011-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a43e1837b2c7e48734023bbefb3c0a8a8617a83b9170af4158499de025f16354
3
+ size 440419456
model-00012-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f92f4f6b01f735780c09a0a86e18fb86ede43cc4df3762cc96dbcb09ba329340
3
+ size 491814488
model-00013-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc9581978ba96dc56a777904886eaa8dc101ce0d24abc15bb686478fdd3c38d9
3
+ size 440419456
model-00014-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1899e9342e92a5cca8074a3ac4683299c22489727898ee6cf02fb095d4b08d57
3
+ size 491814488
model-00015-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68041fc50c9a992ad9402165b0e6375ee45acbfe3d49391f7d9812805c305f90
3
+ size 440419456
model-00016-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b930c5cf367d925bbc2562f9087aea0788bdc7bcc4d5e7435761398de56e0b31
3
+ size 491814488
model-00017-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3185ded95171ba1ac1c85f80451f33c386f8115b8ec46e244fd05cd8f35768
3
+ size 440419448
model-00018-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8626b0635cd70b0003d8f943ec57b61e317026913e006cf6dd72e574043fd7d
3
+ size 491814488
model-00019-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f7f9d14869fb081ff5f550cc4da45229c4a42962d4ba35d9b6add97dd987dbb
3
+ size 440419456
model-00020-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5806fbf507611b59aed6d8851eaeb80f56fee3db192da7ca46454c53e86a3f02
3
+ size 491814488
model-00021-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92ea42bce93a5ec6b1018a7b15d5bffc94e5200c059bffc96b3d19f9dc695881
3
+ size 440419456
model-00022-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87902d34227652035d06b50a4ba8c047b46c07eeb7a30f3e4379e57b553efc5d
3
+ size 491814488
model-00023-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ebd7864156fb16993d4140724319d266de6d4f69c07c8feb028e5c1bef98e0b
3
+ size 440419456
model-00024-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743ec06fc677a678f60e1202042cff10afa4c0a0dbbc9cbd58dcda5bde19903c
3
+ size 491814488
model-00025-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4daae79662223bc8688bdfa8e45e8130b888ed3803e4de1b31148c42f1fac6a2
3
+ size 499164264
model-00026-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef7b0b7a1ac311c7793f0ccdc432356dcd35515dfd5f7ae7b6f1e91ee67d2c7
3
+ size 407372152
model-00027-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d6fea6878836b230e741f1bd1f67a34df18eb2da5620366bcaeec099313121
3
+ size 491814488
model-00028-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70eb8124cc8df3863c3216fc8670acc234f28e98c0ab7149e3aad6d0b1ecf397
3
+ size 440419456
model-00029-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b07ba94c28f0c7c5c040746e5b0222c9b782675d94f9457520f14bc45777e4
3
+ size 491814488
model-00030-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea10e56c2155902e3f22bb9b953b148b224ea3976c82f79d87b261ca7af62b2
3
+ size 440419456
model-00031-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3beb134f83e403c44cc737277749ba6812414b4f58bdf5cc8fbac1d8cce141d6
3
+ size 491814488
model-00032-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ed6ed4bd2b3f2861039fd5734cbaa05d3547ed3f0ac19f0e67b08baaff18fb0
3
+ size 440419456
model-00033-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859355432e7f900e68df84de3d6ac0b877bcbe1a14f42886441b6f9d56b4376e
3
+ size 491814488
model-00034-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02d2728c3f8e86e65effb6bc193fa30775cea5b7ff4913379a9bc4f1fb4a1de6
3
+ size 499156992
model-00035-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267e344efba14c30d2160b75f155583fb06145c6c7fc7f9bdda29af5ac001f06
3
+ size 466116976
model-00036-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c7ba282060d810477c383bcaa6c9f8e46f262dab89ff93b7011eacedd02c33
3
+ size 466116976
model-00037-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b3ef2f91c45df6d8a6cc0f6001d5af7369817ad9fb32ac7eb7d6d14e9ec66b0
3
+ size 466116968
model-00038-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02a850658dfa9b48efe80e3c1727c5227800fcbcd8e96c61b89a9faefb08e801
3
+ size 466124240
model-00039-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0256e06431d49aab7783f9afe41fa6e99320d0473b2de94c7e0afa192f597d15
3
+ size 407372152
model-00040-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0254127912775f125b38376aacd05632e60747036e457e3f9d29e389aa078016
3
+ size 491814472
model-00041-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee34766129058178058c857b12743762159a7bcedabb9e6bf44a88e6448d7d59
3
+ size 440419448
model-00042-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9017c535e8e7b712137e013c3fa763211b52c0b19bf97690443345296171909f
3
+ size 491814472
model-00043-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bea8defe4843fe8855c8410bbe78f9b4d109fc8f7b6fd01009b53a64697c68a
3
+ size 440419448
model-00044-of-00051.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b33619c3d5aa06ec18791b06cf37aff7e0a519bf682839051cc0e814e2e4d236
3
+ size 491814480