Kquant03 commited on
Commit
fd0cfae
1 Parent(s): 9256c17

Upload 22 files

Browse files
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kyujinpy/Sakura-SOLAR-Instruct",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "mixtral",
16
+ "num_attention_heads": 32,
17
+ "num_experts_per_tok": 2,
18
+ "num_hidden_layers": 48,
19
+ "num_key_value_heads": 8,
20
+ "num_local_experts": 8,
21
+ "output_router_logits": false,
22
+ "pad_token_id": 2,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
26
+ "rope_theta": 10000.0,
27
+ "router_aux_loss_coef": 0.001,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float16",
31
+ "transformers_version": "4.37.0.dev0",
32
+ "use_cache": true,
33
+ "vocab_size": 32000
34
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model: kyujinpy/Sakura-SOLAR-Instruct
2
+ gate_mode: hidden
3
+ dtype: bfloat16
4
+ experts:
5
+ - source_model: PracticeLLM/SOLAR-tail-10.7B-Merge-v1.0
6
+ positive_prompts:
7
+ - "helpful"
8
+ - "Relevant"
9
+ - "Factual"
10
+ - "Precise"
11
+ - source_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
12
+ positive_prompts:
13
+ - "Math"
14
+ - "Science"
15
+ negative_prompts:
16
+ - "inaccurate"
17
+ - "incorrect"
18
+ - source_model: kyujinpy/Sakura-SOLAR-Instruct
19
+ positive_prompts:
20
+ - "discuss"
21
+ - "chat"
22
+ - "culture"
23
+ - "world"
24
+ negative_prompts:
25
+ - "Sorry"
26
+ - "As an AI"
27
+ - "cannot"
28
+ - "not capable"
29
+ - source_model: NousResearch/Nous-Hermes-2-SOLAR-10.7B
30
+ positive_prompts:
31
+ - "calculate"
32
+ - "compute"
33
+ - "solve"
34
+ - "work"
35
+ negative_prompts:
36
+ - "mistake"
37
+ - "inaccurate"
38
+ - source_model: upstage/SOLAR-10.7B-Instruct-v1.0
39
+ positive_prompts:
40
+ - "assist"
41
+ - "logic"
42
+ - "sense"
43
+ - source_model: kodonho/SolarM-SakuraSolar-SLERP
44
+ positive_prompts:
45
+ - "form"
46
+ - "connect"
47
+ - "try"
48
+ negative_prompts:
49
+ - "cannot"
50
+ - "incapable"
51
+ - source_model: kyujinpy/Sakura-SOLAR-Instruct
52
+ positive_prompts:
53
+ - "percieve"
54
+ - "discern"
55
+ - "recognize"
56
+ negative_prompts:
57
+ - "don't"
58
+ - "cannot"
59
+ - source_model: kyujinpy/Sakura-SOLAR-Instruct
60
+ positive_prompts:
61
+ - "core"
62
+ - "common"
63
+ - "basic"
64
+ - "intuitive"
65
+ negative_prompts:
66
+ - "boring"
67
+ - "lifeless"
model-00001-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:838942c2fe1e5565e61020018248d2df1306785957738862c924e9b5b1439dca
3
+ size 9919946528
model-00002-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335821cc67c758adaf3463ce246f83a922c55b64885fb359883c56a17394dd56
3
+ size 9982454760
model-00003-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41dd226dce3490c924981789ff464419ce2cff86e94ecb08b20bb0410cdb8e7
3
+ size 9982454760
model-00004-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78045917f54f2a2309c1642155c8c3dbd89bcd18e7885737ab2e33ca7d8ca322
3
+ size 9982454760
model-00005-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:488b9b5de694a45058d6ad14135c6896524251e5d71121558b340a8833a70116
3
+ size 9982454720
model-00006-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b865e6431b9ba3bd59ddd3ef7cfaa44437f1cf115c01268475d1e2b8fc587de5
3
+ size 9982454712
model-00007-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3afda87fc2d72c840388cecbc03d243960b6817563f4318f4d9f40f27c1c50d9
3
+ size 9982454760
model-00008-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154b6b039023319b2ea886dda6d3ad3f448cbf3049a32e09c79af6cc3ab14699
3
+ size 9982454760
model-00009-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35b4dadfd1b5b9c9c10055b192d9eb275ddbc8a4d0240c5c526cabf548cb6cd9
3
+ size 9982454760
model-00010-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfdd088ceaf77cb99245689245f11d9d572301dae0d47a512e9163c21773c85c
3
+ size 9982454680
model-00011-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7c30c57d124953df0518648584477319b50ef7cf6b0ee88a41c8ce8405d75e8
3
+ size 9982454752
model-00012-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:438b99565b16e0697a9c83691eb11c5bef19a9a4c8298265447a5ccfac00b9e2
3
+ size 9982454760
model-00013-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcedc43670d7673a7108a000346598352ee714492bab05ab3ba81b3b9ed69dad
3
+ size 9982454760
model-00014-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca793714f2c1ffaf90ae0978b5014561d60b90172ca64d53e58f0a3be770cc5
3
+ size 9999648648
model-00015-of-00015.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43ce2083a134d058867894ab63830d7d0b82db07fbc978c7c0373bd2945c2d85
3
+ size 137369408
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 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "</s>",
39
+ "legacy": true,
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "<s>",
42
+ "sp_model_kwargs": {},
43
+ "spaces_between_special_tokens": false,
44
+ "tokenizer_class": "LlamaTokenizer",
45
+ "unk_token": "<unk>",
46
+ "use_default_system_prompt": true
47
+ }