Hugging Face's logo

SanjiWatsuki
/
TinyMixtral-32x248M

Text Generation
Transformers
Safetensors
mixtral
Merge
mergekit
lazymergekit
text-generation-inference
Inference Endpoints
Model card Files Community
SanjiWatsuki commited on
Commit
2b448ac
•
1 Parent(s): 87e63c6

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. README.md +84 -0
  2. config.json +30 -0
  3. mergekit_moe_config.yml +69 -0
  4. model-00001-of-00001.safetensors +3 -0
  5. model.safetensors.index.json +0 -0
  6. special_tokens_map.json +28 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +89 -0
README.md ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - merge
5
+ - mergekit
6
+ - lazymergekit
7
+ ---
8
+
9
+ # TinyMixtral-32x248M
10
+
11
+ TinyMixtral-32x248M is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
12
+
13
+ ## 🧩 Configuration
14
+
15
+ ```yaml
16
+ base_model: Locutusque/TinyMistral-248M
17
+ gate_mode: random
18
+ dtype: bfloat16
19
+ experts:
20
+ - source_model: Locutusque/TinyMistral-248M
21
+ positive_prompts: [""]
22
+ - source_model: Locutusque/TinyMistral-248M
23
+ positive_prompts: [""]
24
+ - source_model: Locutusque/TinyMistral-248M
25
+ positive_prompts: [""]
26
+ - source_model: Locutusque/TinyMistral-248M
27
+ positive_prompts: [""]
28
+ - source_model: Locutusque/TinyMistral-248M
29
+ positive_prompts: [""]
30
+ - source_model: Locutusque/TinyMistral-248M
31
+ positive_prompts: [""]
32
+ - source_model: Locutusque/TinyMistral-248M
33
+ positive_prompts: [""]
34
+ - source_model: Locutusque/TinyMistral-248M
35
+ positive_prompts: [""]
36
+ - source_model: Locutusque/TinyMistral-248M
37
+ positive_prompts: [""]
38
+ - source_model: Locutusque/TinyMistral-248M
39
+ positive_prompts: [""]
40
+ - source_model: Locutusque/TinyMistral-248M
41
+ positive_prompts: [""]
42
+ - source_model: Locutusque/TinyMistral-248M
43
+ positive_prompts: [""]
44
+ - source_model: Locutusque/TinyMistral-248M
45
+ positive_prompts: [""]
46
+ - source_model: Locutusque/TinyMistral-248M
47
+ positive_prompts: [""]
48
+ - source_model: Locutusque/TinyMistral-248M
49
+ positive_prompts: [""]
50
+ - source_model: Locutusque/TinyMistral-248M
51
+ positive_prompts: [""]
52
+ - source_model: Locutusque/TinyMistral-248M
53
+ positive_prompts: [""]
54
+ - source_model: Locutusque/TinyMistral-248M
55
+ positive_prompts: [""]
56
+ - source_model: Locutusque/TinyMistral-248M
57
+ positive_prompts: [""]
58
+ - source_model: Locutusque/TinyMistral-248M
59
+ positive_prompts: [""]
60
+ - source_model: Locutusque/TinyMistral-248M
61
+ positive_prompts: [""]
62
+ - source_model: Locutusque/TinyMistral-248M
63
+ positive_prompts: [""]
64
+ - source_model: Locutusque/TinyMistral-248M
65
+ positive_prompts: [""]
66
+ - source_model: Locutusque/TinyMistral-248M
67
+ positive_prompts: [""]
68
+ - source_model: Locutusque/TinyMistral-248M
69
+ positive_prompts: [""]
70
+ - source_model: Locutusque/TinyMistral-248M
71
+ positive_prompts: [""]
72
+ - source_model: Locutusque/TinyMistral-248M
73
+ positive_prompts: [""]
74
+ - source_model: Locutusque/TinyMistral-248M
75
+ positive_prompts: [""]
76
+ - source_model: Locutusque/TinyMistral-248M
77
+ positive_prompts: [""]
78
+ - source_model: Locutusque/TinyMistral-248M
79
+ positive_prompts: [""]
80
+ - source_model: Locutusque/TinyMistral-248M
81
+ positive_prompts: [""]
82
+ - source_model: Locutusque/TinyMistral-248M
83
+ positive_prompts: [""]
84
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Locutusque/TinyMistral-248M",
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": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 32,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 12,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 32,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-06,
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": "4.37.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 32005
30
+ }
mergekit_moe_config.yml ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ base_model: Locutusque/TinyMistral-248M
3
+ gate_mode: random
4
+ dtype: bfloat16
5
+ experts:
6
+ - source_model: Locutusque/TinyMistral-248M
7
+ positive_prompts: [""]
8
+ - source_model: Locutusque/TinyMistral-248M
9
+ positive_prompts: [""]
10
+ - source_model: Locutusque/TinyMistral-248M
11
+ positive_prompts: [""]
12
+ - source_model: Locutusque/TinyMistral-248M
13
+ positive_prompts: [""]
14
+ - source_model: Locutusque/TinyMistral-248M
15
+ positive_prompts: [""]
16
+ - source_model: Locutusque/TinyMistral-248M
17
+ positive_prompts: [""]
18
+ - source_model: Locutusque/TinyMistral-248M
19
+ positive_prompts: [""]
20
+ - source_model: Locutusque/TinyMistral-248M
21
+ positive_prompts: [""]
22
+ - source_model: Locutusque/TinyMistral-248M
23
+ positive_prompts: [""]
24
+ - source_model: Locutusque/TinyMistral-248M
25
+ positive_prompts: [""]
26
+ - source_model: Locutusque/TinyMistral-248M
27
+ positive_prompts: [""]
28
+ - source_model: Locutusque/TinyMistral-248M
29
+ positive_prompts: [""]
30
+ - source_model: Locutusque/TinyMistral-248M
31
+ positive_prompts: [""]
32
+ - source_model: Locutusque/TinyMistral-248M
33
+ positive_prompts: [""]
34
+ - source_model: Locutusque/TinyMistral-248M
35
+ positive_prompts: [""]
36
+ - source_model: Locutusque/TinyMistral-248M
37
+ positive_prompts: [""]
38
+ - source_model: Locutusque/TinyMistral-248M
39
+ positive_prompts: [""]
40
+ - source_model: Locutusque/TinyMistral-248M
41
+ positive_prompts: [""]
42
+ - source_model: Locutusque/TinyMistral-248M
43
+ positive_prompts: [""]
44
+ - source_model: Locutusque/TinyMistral-248M
45
+ positive_prompts: [""]
46
+ - source_model: Locutusque/TinyMistral-248M
47
+ positive_prompts: [""]
48
+ - source_model: Locutusque/TinyMistral-248M
49
+ positive_prompts: [""]
50
+ - source_model: Locutusque/TinyMistral-248M
51
+ positive_prompts: [""]
52
+ - source_model: Locutusque/TinyMistral-248M
53
+ positive_prompts: [""]
54
+ - source_model: Locutusque/TinyMistral-248M
55
+ positive_prompts: [""]
56
+ - source_model: Locutusque/TinyMistral-248M
57
+ positive_prompts: [""]
58
+ - source_model: Locutusque/TinyMistral-248M
59
+ positive_prompts: [""]
60
+ - source_model: Locutusque/TinyMistral-248M
61
+ positive_prompts: [""]
62
+ - source_model: Locutusque/TinyMistral-248M
63
+ positive_prompts: [""]
64
+ - source_model: Locutusque/TinyMistral-248M
65
+ positive_prompts: [""]
66
+ - source_model: Locutusque/TinyMistral-248M
67
+ positive_prompts: [""]
68
+ - source_model: Locutusque/TinyMistral-248M
69
+ positive_prompts: [""]
model-00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e93682973abd97e8fedeebf9e84fe97ad7f18669158e21fe0c43065e6d41655
3
+ size 9858681752
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 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|ASSISTANT|>",
4
+ "<|USER|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|bos|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": "<|bos|>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
30
+ "content": "<|bos|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "[PAD]",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|ASSISTANT|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|USER|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ }
69
+ },
70
+ "additional_special_tokens": [
71
+ "<|ASSISTANT|>",
72
+ "<|USER|>"
73
+ ],
74
+ "bos_token": "<|bos|>",
75
+ "clean_up_tokenization_spaces": false,
76
+ "eos_token": "<|endoftext|>",
77
+ "legacy": true,
78
+ "max_length": 1536,
79
+ "model_max_length": 1000000000000000019884624838656,
80
+ "pad_token": "<|bos|>",
81
+ "sp_model_kwargs": {},
82
+ "spaces_between_special_tokens": false,
83
+ "stride": 0,
84
+ "tokenizer_class": "LlamaTokenizer",
85
+ "truncation_side": "right",
86
+ "truncation_strategy": "longest_first",
87
+ "unk_token": "<unk>",
88
+ "use_default_system_prompt": true
89
+ }