Hugging Face's logo

nm-testing
/
test-w4a16-mixtral-actorder-group

Safetensors
mixtral
compressed-tensors
Model card Files Community
Eldar Kurtic commited on
Commit
4f8a8e4
·
1 Parent(s): 8b5dafd

add model

Browse files
Files changed (11) hide show
  1. config.json +102 -0
  2. generation_config.json +6 -0
  3. model-00001-of-00005.safetensors +3 -0
  4. model-00002-of-00005.safetensors +3 -0
  5. model-00003-of-00005.safetensors +3 -0
  6. model-00004-of-00005.safetensors +3 -0
  7. model-00005-of-00005.safetensors +3 -0
  8. model.safetensors.index.json +0 -0
  9. special_tokens_map.json +23 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +43 -0
config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/eldar/.cache/huggingface/hub/models--mistralai--Mixtral-8x7B-v0.1/snapshots/ffe1a706bacbd5abddc5ff99432ee38f7e0662fb",
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": 8,
20
+ "output_router_logits": false,
21
+ "quantization_config": {
22
+ "config_groups": {
23
+ "group_0": {
24
+ "input_activations": null,
25
+ "output_activations": null,
26
+ "targets": [
27
+ "Linear"
28
+ ],
29
+ "weights": {
30
+ "actorder": "group",
31
+ "block_structure": null,
32
+ "dynamic": false,
33
+ "group_size": 128,
34
+ "num_bits": 4,
35
+ "observer": "minmax",
36
+ "observer_kwargs": {},
37
+ "strategy": "group",
38
+ "symmetric": true,
39
+ "type": "int"
40
+ }
41
+ }
42
+ },
43
+ "format": "pack-quantized",
44
+ "global_compression_ratio": 2.096987748979177,
45
+ "ignore": [
46
+ "model.layers.0.block_sparse_moe.gate",
47
+ "model.layers.1.block_sparse_moe.gate",
48
+ "model.layers.2.block_sparse_moe.gate",
49
+ "model.layers.3.block_sparse_moe.gate",
50
+ "model.layers.4.block_sparse_moe.gate",
51
+ "model.layers.5.block_sparse_moe.gate",
52
+ "model.layers.6.block_sparse_moe.gate",
53
+ "model.layers.7.block_sparse_moe.gate",
54
+ "model.layers.8.block_sparse_moe.gate",
55
+ "model.layers.9.block_sparse_moe.gate",
56
+ "model.layers.10.block_sparse_moe.gate",
57
+ "model.layers.11.block_sparse_moe.gate",
58
+ "model.layers.12.block_sparse_moe.gate",
59
+ "model.layers.13.block_sparse_moe.gate",
60
+ "model.layers.14.block_sparse_moe.gate",
61
+ "model.layers.15.block_sparse_moe.gate",
62
+ "model.layers.16.block_sparse_moe.gate",
63
+ "model.layers.17.block_sparse_moe.gate",
64
+ "model.layers.18.block_sparse_moe.gate",
65
+ "model.layers.19.block_sparse_moe.gate",
66
+ "model.layers.20.block_sparse_moe.gate",
67
+ "model.layers.21.block_sparse_moe.gate",
68
+ "model.layers.22.block_sparse_moe.gate",
69
+ "model.layers.23.block_sparse_moe.gate",
70
+ "model.layers.24.block_sparse_moe.gate",
71
+ "model.layers.25.block_sparse_moe.gate",
72
+ "model.layers.26.block_sparse_moe.gate",
73
+ "model.layers.27.block_sparse_moe.gate",
74
+ "model.layers.28.block_sparse_moe.gate",
75
+ "model.layers.29.block_sparse_moe.gate",
76
+ "model.layers.30.block_sparse_moe.gate",
77
+ "model.layers.31.block_sparse_moe.gate",
78
+ "lm_head"
79
+ ],
80
+ "kv_cache_scheme": null,
81
+ "quant_method": "compressed-tensors",
82
+ "quantization_status": "compressed",
83
+ "sparsity_config": {
84
+ "format": "dense",
85
+ "global_sparsity": 0.15719747857965694,
86
+ "ignore": [],
87
+ "registry_requires_subclass": false,
88
+ "sparsity_structure": "unstructured",
89
+ "targets": []
90
+ }
91
+ },
92
+ "rms_norm_eps": 1e-05,
93
+ "rope_theta": 1000000.0,
94
+ "router_aux_loss_coef": 0.02,
95
+ "router_jitter_noise": 0.0,
96
+ "sliding_window": null,
97
+ "tie_word_embeddings": false,
98
+ "torch_dtype": "bfloat16",
99
+ "transformers_version": "4.46.2",
100
+ "use_cache": false,
101
+ "vocab_size": 32000
102
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.46.2"
6
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad645dc960494eb26c54d3f60432f5990d89459d18f92fff9932943a0d48d43
3
+ size 4991088336
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17dcc69815aa7f1b9577416f490c0845de0ff555b93831c614d1cff762c77bee
3
+ size 4979999232
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a55552a4b177d30e189f8d1338246aeb3e539f3458d2d013ddc7e36ba85aab74
3
+ size 4971440752
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d3923b3c9e6c2fc231e5ebac63c909baddf30a249a46662ea15e0c50a7437a7
3
+ size 4971440760
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae609477cf45c453b37d075786c09e09fed0427808ce201ddca4d821579e2d3
3
+ size 4583878624
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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "additional_special_tokens": [],
32
+ "bos_token": "<s>",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
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
+ }