Holy-fox commited on
Commit
0f19b66
·
verified ·
1 Parent(s): 4cc1a89

Upload 76 files

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 +51 -3
  3. added_tokens.json +24 -0
  4. config.json +29 -0
  5. mergekit_config.yml +17 -0
  6. merges.txt +0 -0
  7. model-00001-of-00066.safetensors +3 -0
  8. model-00002-of-00066.safetensors +3 -0
  9. model-00003-of-00066.safetensors +3 -0
  10. model-00004-of-00066.safetensors +3 -0
  11. model-00005-of-00066.safetensors +3 -0
  12. model-00006-of-00066.safetensors +3 -0
  13. model-00007-of-00066.safetensors +3 -0
  14. model-00008-of-00066.safetensors +3 -0
  15. model-00009-of-00066.safetensors +3 -0
  16. model-00010-of-00066.safetensors +3 -0
  17. model-00011-of-00066.safetensors +3 -0
  18. model-00012-of-00066.safetensors +3 -0
  19. model-00013-of-00066.safetensors +3 -0
  20. model-00014-of-00066.safetensors +3 -0
  21. model-00015-of-00066.safetensors +3 -0
  22. model-00016-of-00066.safetensors +3 -0
  23. model-00017-of-00066.safetensors +3 -0
  24. model-00018-of-00066.safetensors +3 -0
  25. model-00019-of-00066.safetensors +3 -0
  26. model-00020-of-00066.safetensors +3 -0
  27. model-00021-of-00066.safetensors +3 -0
  28. model-00022-of-00066.safetensors +3 -0
  29. model-00023-of-00066.safetensors +3 -0
  30. model-00024-of-00066.safetensors +3 -0
  31. model-00025-of-00066.safetensors +3 -0
  32. model-00026-of-00066.safetensors +3 -0
  33. model-00027-of-00066.safetensors +3 -0
  34. model-00028-of-00066.safetensors +3 -0
  35. model-00029-of-00066.safetensors +3 -0
  36. model-00030-of-00066.safetensors +3 -0
  37. model-00031-of-00066.safetensors +3 -0
  38. model-00032-of-00066.safetensors +3 -0
  39. model-00033-of-00066.safetensors +3 -0
  40. model-00034-of-00066.safetensors +3 -0
  41. model-00035-of-00066.safetensors +3 -0
  42. model-00036-of-00066.safetensors +3 -0
  43. model-00037-of-00066.safetensors +3 -0
  44. model-00038-of-00066.safetensors +3 -0
  45. model-00039-of-00066.safetensors +3 -0
  46. model-00040-of-00066.safetensors +3 -0
  47. model-00041-of-00066.safetensors +3 -0
  48. model-00042-of-00066.safetensors +3 -0
  49. model-00043-of-00066.safetensors +3 -0
  50. model-00044-of-00066.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 CHANGED
@@ -1,3 +1,51 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-32B-Instruct
4
+ - karakuri-ai/karakuri-lm-32b-thinking-2501-exp
5
+ library_name: transformers
6
+ tags:
7
+ - mergekit
8
+ - merge
9
+
10
+ ---
11
+ # SKYDRIVE-32B-v0.1
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) as a base.
19
+
20
+ ### Models Merged
21
+
22
+ The following models were included in the merge:
23
+ * SKYDRIVE_element_jp_02
24
+ * SKYDRIVE_element_jp_03
25
+ * [karakuri-ai/karakuri-lm-32b-thinking-2501-exp](https://huggingface.co/karakuri-ai/karakuri-lm-32b-thinking-2501-exp)
26
+ * SKYCAVE_element_Sky_jp
27
+ * SKYDRIVE_element_jp_04
28
+
29
+ ### Configuration
30
+
31
+ The following YAML configuration was used to produce this model:
32
+
33
+ ```yaml
34
+ merge_method: model_stock
35
+
36
+ base_model: Qwen/Qwen2.5-32B-Instruct
37
+
38
+ models:
39
+ - model: karakuri-ai/karakuri-lm-32b-thinking-2501-exp
40
+ - model: SKYCAVE_element_Sky_jp
41
+ - model: SKYDRIVE_element_jp_02
42
+ - model: SKYDRIVE_element_jp_03
43
+ - model: SKYDRIVE_element_jp_04
44
+
45
+ dtype: bfloat16
46
+
47
+ pad_to_multiple_of: 512
48
+ tokenizer_source: base
49
+
50
+ name: SKYDRIVE-32B-v0.1
51
+ ```
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/Qwen2.5-32B-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": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 64,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.48.1",
26
+ "use_cache": true,
27
+ "use_sliding_window": false,
28
+ "vocab_size": 151665
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ merge_method: model_stock
2
+
3
+ base_model: Qwen/Qwen2.5-32B-Instruct
4
+
5
+ models:
6
+ - model: karakuri-ai/karakuri-lm-32b-thinking-2501-exp
7
+ - model: SKYCAVE_element_Sky_jp
8
+ - model: SKYDRIVE_element_jp_02
9
+ - model: SKYDRIVE_element_jp_03
10
+ - model: SKYDRIVE_element_jp_04
11
+
12
+ dtype: bfloat16
13
+
14
+ pad_to_multiple_of: 512
15
+ tokenizer_source: base
16
+
17
+ name: SKYDRIVE-32B-v0.1
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b838b5559b8f0419653f5975f2a37d11d86249352fb0395c90ccea89ace267ea
3
+ size 1553049728
model-00002-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d128c6122d90443fa6568b72320da03a298aaecffeaab53ce251895ef9e89a7
3
+ size 1553049744
model-00003-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1e76d847d21a1a85d4df2eee7a18d18c83f671640c677187bea62e1e7af5730
3
+ size 975222224
model-00004-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c349643d82b96e09a19bf3a47d238ca9fdfa411b181cd75988090f05969bd541
3
+ size 975211880
model-00005-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa1246a9e249c1159bdcac64d423b079f49312bf5d60ad1367c456a0d9ae548
3
+ size 975211888
model-00006-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f584dc1bef1ff8023496dbf85010ca38354f701bf16faffe48718685da5eea93
3
+ size 975211888
model-00007-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fe6025b0f6803c2fa764c15023190f765fa4ad2fc2471a609e73961c1230e01
3
+ size 975211888
model-00008-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf715dbe53446c265603e2a9dae6080080c32e0a203bcb0d13810ddd68fc9280
3
+ size 975211888
model-00009-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ea19398d6fe0bcaf23b1d1d5ce2d212bf064f5851c0c003c7b441c98734345
3
+ size 975211888
model-00010-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f41362fccab14df8b45b35eda6ba39f1d2823f92ab7e3a866d9876ac67b7f7
3
+ size 975211888
model-00011-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ee587a015f93669e6d838d239b77cb0f1798219aa53835acd9a50953b46be6
3
+ size 975211888
model-00012-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa993a3047ee3c285b9a06144e9138cf49631d128fbb72e619fdd7d881ce3a74
3
+ size 975211888
model-00013-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daffed52b416697f8ebe96837b8b032a03e24fffb6f34f4e10b6d1e9bd29dc51
3
+ size 975211888
model-00014-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0e1b6014029faefcd787ecf08079c33c26a834d44b5008a911896db43bf599f
3
+ size 975211888
model-00015-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6426f0d6a3372fba70bbd6efe3d394fe0615463a08d63c4ea869ea68f6eefbc9
3
+ size 975211880
model-00016-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b1b8cc7f72ff1c59226df8ab35e1931784513ba534425ef0fe5081afffa9a40
3
+ size 975211888
model-00017-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a481918c21e610d11b9da1d66674e50eae0a9ac96aa3b139ef34f4c35b6b917
3
+ size 975211888
model-00018-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfab5fafbad15a9f802de5ce807ce2cbbc5c11ca2805edb61608880df2cdeacb
3
+ size 975211888
model-00019-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def64f818c63232966655fdb4da31294329ab017a56986af7e3f5b346d2a0a11
3
+ size 975211888
model-00020-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69ce8f6fc03b45d4a472875572537ccea414d9b7a79de0cfb71d4312b1d8a3ef
3
+ size 975211888
model-00021-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e68c4c5dd6eecff9f536b2a74e5775342e2a3f8c0f384bef11438807ca0741d
3
+ size 975211888
model-00022-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb217d1d0236c0924cb39ca112937fe37ab5ed52f6b63492755c5eda5f28ec62
3
+ size 975211888
model-00023-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b5b16cf43ff44ba6389b3a155176697d354e1fc9490b31d4dbf5d413bd08ce0
3
+ size 975211888
model-00024-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ab301c7b7a32ccf28be5a03cda5691a5e3da61cd44964cbb9351dcb30669df
3
+ size 975211888
model-00025-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30970f7a0e0c6a39a0def829fb8c5a950b7123ad4867d60a8cb183b426ef6c2b
3
+ size 975211888
model-00026-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e1321008342cae28cb863ec5449689f140ad091a8cf38b5b0b7ba9ef0d877bd
3
+ size 975211880
model-00027-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:416f3eebe14544ed7b22aa390b463f378cd7d9f39f02c931a58fffa9c905f168
3
+ size 975211888
model-00028-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89157022f438c20979d8deee24f982579720b17deaf47ced9d1f6a1d9f17c16d
3
+ size 975211888
model-00029-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:380ae5f6c9189db458e6990657e9e89928805a48c4f01f6c7324865ca9c87847
3
+ size 975211888
model-00030-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:516acf4f024f518135843e8324d9a2e0387dbe9c48999fcc18e8707a79ce18a8
3
+ size 975211888
model-00031-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ede8368a5a8b00add5ac2e567febab72376803fb1ed3918be08c2489b67a67e7
3
+ size 975211888
model-00032-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61f1d76f64e8ed2388a5664fb8cdb691c57a1489bed521a7a7bbf1546b082722
3
+ size 975211888
model-00033-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00cf361e4d8a630bec2d62f61f86662d90e16aeeb364c116edfcdca9cec579b7
3
+ size 975211888
model-00034-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ec32909c85739c7c5b690ff66f941a8e8a6e9bc5ac4afd819bf61db8e52d4f
3
+ size 975211888
model-00035-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5739275dff38cf1afab8d80caa74c0344a8569178bee67a2756154a43620b200
3
+ size 975211888
model-00036-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd1f808e568528b3c6e601a6e48dc9a5ab0aaa0dff09f3cb3a530884c7f8b214
3
+ size 975211888
model-00037-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54cca55ac12943dbdad3e93082e26de8e88bea184638037df55e73fb20548792
3
+ size 975211880
model-00038-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c4b674ba1e34096589c8c3c4b75d1577d275da7cb3894d02e2d4a9fb15d7b5
3
+ size 975211888
model-00039-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab91f4bdcce2d8b82a8fdc39be23eb8e35ae35dff63fa467fca6485cdffe993
3
+ size 975211888
model-00040-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9131af14b09aad2d37d903679a0b68a564488f7168758d0acd609ebd4e0e016
3
+ size 975211888
model-00041-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:429b55b153dbc3fc21f743b8abbf622b75f48ea175f0cf5abf0cc0ed743af1cb
3
+ size 975211888
model-00042-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:959bce79cbc0a609f16bc8eb845269048918973302fae5d583e4723e90373fb3
3
+ size 975211888
model-00043-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:487f846f829a3eed1cfca6ab6b46c46dae028e8e0e457babf2f73435fbe2236e
3
+ size 975211888
model-00044-of-00066.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ab97b1f8f49835bb89d1a91be851932552c2963a78325a7e392da858416ea1e
3
+ size 975211888