Hugging Face's logo

Kquant03
/
Azathoth-16x7B-bf16

Text Generation
Transformers
Safetensors
English
mixtral
Mixture of Experts
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
1
Kquant03 commited on
Commit
57562f8
·
verified ·
1 Parent(s): cdcf12e

Upload 26 files

Browse files
Files changed (26) hide show
  1. config.json +31 -0
  2. mergekit_moe_config.yml +84 -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 +29 -0
  24. tokenizer.json +0 -0
  25. tokenizer.model +3 -0
  26. tokenizer_config.json +49 -0
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "alnrg2arg/test3_sft_16bit",
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": "float16",
27
+ "transformers_version": "4.37.1",
28
+ "unsloth_version": "2024.1",
29
+ "use_cache": false,
30
+ "vocab_size": 32000
31
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: alnrg2arg/test3_sft_16bit
2
+ gate_mode: hidden
3
+ dtype: float16
4
+ experts:
5
+ - source_model: alnrg2arg/test3_sft_16bit
6
+ positive_prompts:
7
+ - " "
8
+ negative_prompts:
9
+ - " "
10
+ - source_model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
11
+ positive_prompts:
12
+ - " "
13
+ negative_prompts:
14
+ - " "
15
+ - source_model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
16
+ positive_prompts:
17
+ - " "
18
+ negative_prompts:
19
+ - " "
20
+ - source_model: alnrg2arg/test3_sft_16bit
21
+ positive_prompts:
22
+ - " "
23
+ negative_prompts:
24
+ - " "
25
+ - source_model: mlabonne/Daredevil-7B
26
+ positive_prompts:
27
+ - " "
28
+ negative_prompts:
29
+ - " "
30
+ - source_model: senseable/garten2-7b
31
+ positive_prompts:
32
+ - " "
33
+ negative_prompts:
34
+ - " "
35
+ - source_model: mlabonne/Daredevil-7B
36
+ positive_prompts:
37
+ - " "
38
+ negative_prompts:
39
+ - " "
40
+ - source_model: alnrg2arg/test3_sft_16bit
41
+ positive_prompts:
42
+ - " "
43
+ negative_prompts:
44
+ - " "
45
+ - source_model: mlabonne/Daredevil-7B
46
+ positive_prompts:
47
+ - " "
48
+ negative_prompts:
49
+ - " "
50
+ - source_model: senseable/garten2-7b
51
+ positive_prompts:
52
+ - " "
53
+ negative_prompts:
54
+ - " "
55
+ - source_model: macadeliccc/WestLake-7B-v2-laser-truthy-dpo
56
+ positive_prompts:
57
+ - " "
58
+ negative_prompts:
59
+ - " "
60
+ - source_model: FelixChao/Severus-7B
61
+ positive_prompts:
62
+ - " "
63
+ negative_prompts:
64
+ - " "
65
+ - source_model: ConvexAI/Metabird-7B
66
+ positive_prompts:
67
+ - " "
68
+ negative_prompts:
69
+ - " "
70
+ - source_model: FelixChao/Severus-7B
71
+ positive_prompts:
72
+ - " "
73
+ negative_prompts:
74
+ - " "
75
+ - source_model: ConvexAI/Metabird-7B
76
+ positive_prompts:
77
+ - " "
78
+ negative_prompts:
79
+ - " "
80
+ - source_model: alnrg2arg/test3_sft_16bit
81
+ positive_prompts:
82
+ - " "
83
+ negative_prompts:
84
+ - " "
model-00001-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a39c076baf39c7ae9a40eaf60aba29fb7a55c9c81ff0fa2901e2e8cb6116b3b
3
+ size 9919813576
model-00002-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e71747ffefcaccd807129be96c51b1153233ffdb3be110c6845457595b7812aa
3
+ size 9982454624
model-00003-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f6b31888eb316ab4b1ed74ad344ba84205a9ff381291cc0144e2dfa9574bc4b
3
+ size 9982454704
model-00004-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40aecf11a0e8edaecfdb77efd1bd49136a0d2ff5210198ff8d530969295668a5
3
+ size 9982454712
model-00005-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d42406ca8f5a7e3452b23dff193e1069f1c9a4a156e5c53538861fdd47433a
3
+ size 9982454704
model-00006-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca5f69e2a4d2e1ae9a9a91f5a39a2708e079d987a32ab77afc7a45563d6e5c1
3
+ size 9982454704
model-00007-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f9247dc351e92e9105d1caed5ce48916e457e252976d00c71d590c3ac08ba25
3
+ size 9982454632
model-00008-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaec34be181f2730584727a5d06ceeea536409528cafda46294d0e24b6a51b84
3
+ size 9982454624
model-00009-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62c8113441ee9f391766883c65295f8172943e75f9ea9aecd7abfc8b943cf4f2
3
+ size 9982454704
model-00010-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d11f2a6fe1b10ecd2c2fdc6c4ecde346dc0215f99ccc54bc8f9b8253991ee6c
3
+ size 9982454704
model-00011-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37e4ab45b2af53796578f1bf7c228ad1018db6aad38aa1ca6ed26074154e2035
3
+ size 9982454704
model-00012-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51311952db3b987c98673658c87f57dc2c9b136aa89404f407f37f4d62f65aa5
3
+ size 9982454704
model-00013-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ece613f4a6db318a631faa7ce1115d0fcaddd23c97306a43dc0605b3effb752b
3
+ size 9982454632
model-00014-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a75d2b4f23af58adea3f1cb2788198f32ff54dfcef8bc487e44a80c53e03c85
3
+ size 9982454624
model-00015-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c8ceb1ca147b151e8738f2855e04a65edd0f1f9fdf1f434232f3509552e0873
3
+ size 9982454704
model-00016-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:382956c28b2a2215eaf0c97dd1657160fd0ed941f9ecdbe3b80f04a2a7db0698
3
+ size 9982454704
model-00017-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ae3fbbc58ed2ae053df2ac7f912630f463e0a0cea296eb8907183b07c5fe6e5
3
+ size 9982454712
model-00018-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d6fa3235022ae303ad1c780324d1cc594984415bc0a411b79319ce5c06ce46
3
+ size 9982454704
model-00019-of-00019.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:035574ef2e06aa559bc609ca8175e9cae90cb0f2e0477d0ac6b21de5f11f8cc8
3
+ size 3980680544
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 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": {
8
+ "content": "<s>",
9
+ "lstrip": false,
10
+ "normalized": false,
11
+ "rstrip": false,
12
+ "single_word": false
13
+ },
14
+ "eos_token": {
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "pad_token": "<s>",
22
+ "unk_token": {
23
+ "content": "<unk>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ }
29
+ }
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<unk>",
32
+ "<s>",
33
+ "</s>"
34
+ ],
35
+ "bos_token": "<s>",
36
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 32768,
41
+ "pad_token": "<s>",
42
+ "padding_side": "left",
43
+ "sp_model_kwargs": {},
44
+ "spaces_between_special_tokens": false,
45
+ "split_special_tokens": false,
46
+ "tokenizer_class": "LlamaTokenizer",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": true
49
+ }