Hugging Face's logo

Kquant03
/
Kaltsit-16x7B-bf16

Text Generation
Transformers
Safetensors
English
mixtral
Mixture of Experts
Merge
text-generation-inference
Inference Endpoints
Model card Files Community
1
Kquant03 commited on
Commit
a1e23dd
•
1 Parent(s): 78d9111

Upload 26 files

Browse files
Files changed (26) hide show
  1. config.json +30 -0
  2. mergekit_moe_config.yml +102 -0
  3. model-00001-of-00019.safetensors +3 -0
  4. model-00002-of-00019.safetensors +3 -0
  5. model-00003-of-00019.safetensors +3 -0
  6. model-00004-of-00019.safetensors +3 -0
  7. model-00005-of-00019.safetensors +3 -0
  8. model-00006-of-00019.safetensors +3 -0
  9. model-00007-of-00019.safetensors +3 -0
  10. model-00008-of-00019.safetensors +3 -0
  11. model-00009-of-00019.safetensors +3 -0
  12. model-00010-of-00019.safetensors +3 -0
  13. model-00011-of-00019.safetensors +3 -0
  14. model-00012-of-00019.safetensors +3 -0
  15. model-00013-of-00019.safetensors +3 -0
  16. model-00014-of-00019.safetensors +3 -0
  17. model-00015-of-00019.safetensors +3 -0
  18. model-00016-of-00019.safetensors +3 -0
  19. model-00017-of-00019.safetensors +3 -0
  20. model-00018-of-00019.safetensors +3 -0
  21. model-00019-of-00019.safetensors +3 -0
  22. model.safetensors.index.json +0 -0
  23. special_tokens_map.json +24 -0
  24. tokenizer.json +0 -0
  25. tokenizer.model +3 -0
  26. tokenizer_config.json +43 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bardsai/jaskier-7b-dpo-v5.6",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 16,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 10000.0,
23
+ "router_aux_loss_coef": 0.001,
24
+ "sliding_window": null,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.39.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: bardsai/jaskier-7b-dpo-v5.6
2
+ gate_mode: hidden
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
6
+ positive_prompts:
7
+ - "IT"
8
+ - "programming"
9
+ - "Science"
10
+ - "Computing"
11
+ - "Processing"
12
+ negative_prompts:
13
+ - "incorrect"
14
+ - source_model: macadeliccc/MonarchLake-7B
15
+ positive_prompts:
16
+ - "Chat"
17
+ - "Discuss"
18
+ negative_prompts:
19
+ - "fictional"
20
+ - source_model: paulml/OmniBeagleSquaredMBX-v3-7B-v2
21
+ positive_prompts:
22
+ - "storywriting"
23
+ - "fiction"
24
+ negative_prompts:
25
+ - "nonfiction"
26
+ - source_model: louisbrulenaudet/Pearl-7B-slerp
27
+ positive_prompts:
28
+ - "Arithmetic"
29
+ negative_prompts:
30
+ - "fictional"
31
+ - source_model: CultriX/NeuralTrix-7B-dpo
32
+ positive_prompts:
33
+ - "stimulating"
34
+ - "interesting"
35
+ negative_prompts:
36
+ - "boring"
37
+ - source_model: FelixChao/Capricorn-7B-DPO
38
+ positive_prompts:
39
+ - "business"
40
+ - "finance"
41
+ negative_prompts:
42
+ - "irresponsible"
43
+ - source_model: CultriX/NeuralTrix-7B-dpo
44
+ positive_prompts:
45
+ - "research"
46
+ - "intriguing"
47
+ negative_prompts:
48
+ - "fictional"
49
+ - source_model: louisbrulenaudet/Pearl-7B-slerp
50
+ positive_prompts:
51
+ - "algebra"
52
+ - "calculus"
53
+ negative_prompts:
54
+ - "inaccurate"
55
+ - source_model: openagi-project/OpenAGI-7B-v0.1
56
+ positive_prompts:
57
+ - "professional"
58
+ - "business"
59
+ negative_prompts:
60
+ - "unprofessional"
61
+ - source_model: FelixChao/Capricorn-7B-DPO
62
+ positive_prompts:
63
+ - "Conceptual"
64
+ - "ideal"
65
+ negative_prompts:
66
+ - "pragmatic"
67
+ - source_model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
68
+ positive_prompts:
69
+ - "technology"
70
+ - "tech"
71
+ negative_prompts:
72
+ - "archaic"
73
+ - source_model: macadeliccc/MonarchLake-7B
74
+ positive_prompts:
75
+ - "pattern"
76
+ - "recognition"
77
+ negative_prompts:
78
+ - "mismatch"
79
+ - source_model: macadeliccc/MonarchLake-7B
80
+ positive_prompts:
81
+ - "positive"
82
+ - "understanding"
83
+ negative_prompts:
84
+ - "safe"
85
+ - source_model: bardsai/jaskier-7b-dpo-v5.6
86
+ positive_prompts:
87
+ - "precise"
88
+ - "accurate"
89
+ negative_prompts:
90
+ - "inaccurate"
91
+ - source_model: bardsai/jaskier-7b-dpo-v5.6
92
+ positive_prompts:
93
+ - "intellectual"
94
+ - "efficient"
95
+ negative_prompts:
96
+ - "stupid"
97
+ - source_model: macadeliccc/MonarchLake-7B
98
+ positive_prompts:
99
+ - "medical"
100
+ - "illness"
101
+ negative_prompts:
102
+ - "poor practices"
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42f1c648b0fd837e80f0a2d281be2dab0b60674137df656d6b7273d27b66eaab
3
+ size 9919813696
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2793fd5bbf723c6910dd6b925df81393f2a4c63350e535f6650e1cc6b800eb4
3
+ size 9982454712
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8826f4fc8b42a2bf7b3ee1015e5e7750762dcc292e0090cc9a71b12d5dbb11d4
3
+ size 9982454792
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c0d266727c85fd9fe1a3c0e98dca21357667a5cf720152820ab258e85013ac
3
+ size 9982454792
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d0531f804829d1e09a0d8d72a59810bda9ee9125a49a962c993d6265e35d1a0
3
+ size 9982454792
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e129c1fe1276db5d7d3814e1f74d86aa90c272c9777f7f78562a13306e1c9c6
3
+ size 9982454792
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4843012947f56518bd3cc1c525f6115a9706cafca03dd4c382f79023e01b4ef
3
+ size 9982454712
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a93ace4e1cb84838fc352aca482bab2d9d091d4c7e0ce5a24e8e3e232da213
3
+ size 9982454712
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd1ea1be0a7e6e00c76cd9b48c94ffabb0ed8993b7f790739381f8c329ab271
3
+ size 9982454792
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa185da78b6e8c6add37d55d1172dba41b903967453dfc5494e27fbe441a8ecc
3
+ size 9982454792
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:197783e8470fb8cf81e2849127f060c244a8ed691b555266e8da77ba55e12508
3
+ size 9982454792
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47896bcadcb7474103596dde2f4f26c3d4fac3434c7b1de6396ba6e29669b8a1
3
+ size 9982454792
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f80a22bb26deef17f5398d2f12385701be4cdab6915ce8b4e9f982166096fc97
3
+ size 9982454712
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652054b800c4f2cf91f4baaacaa75635b9f9518a2c473bce4fcac0f145f2860d
3
+ size 9982454712
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1947760381bd197fcd9cc515412fd0776925ec9c592a026b7d7f9e6767f33a9c
3
+ size 9982454792
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:224ce678020eba2c2e9df942dfb85eec7eca785cbfd59c740a8e53d11173447e
3
+ size 9982454792
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea8081eb546a59ec5bbe4e4f6b3be42e7302f5c86ea6a001a0598279555ecc8
3
+ size 9982454792
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a3d78f575cbb2832d2c076f18f8533449568230d0541b1bc14b20f9aa9b08c
3
+ size 9982454792
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c598b3f04a5f56491d0270688180023b5d0fd9389d9162f3949db98abad79e06
3
+ size 3980680752
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 32768,
36
+ "pad_token": "<s>",
37
+ "padding_side": "left",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }