TheBloke commited on
Commit
3e0d292
1 Parent(s): faddb48

GPTQ model commit

Browse files
config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/process/steelskull_lumosia-moe-4x10.7/source",
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": 4,
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
+ "quantization_config": {
35
+ "bits": 4,
36
+ "group_size": -1,
37
+ "damp_percent": 0.1,
38
+ "desc_act": true,
39
+ "static_groups": false,
40
+ "sym": true,
41
+ "true_sequential": true,
42
+ "model_name_or_path": null,
43
+ "model_file_base_name": "model",
44
+ "quant_method": "gptq",
45
+ "modules_in_block_to_quantize": [
46
+ [
47
+ "self_attn.k_proj",
48
+ "self_attn.v_proj",
49
+ "self_attn.q_proj"
50
+ ],
51
+ [
52
+ "self_attn.o_proj"
53
+ ],
54
+ [
55
+ "block_sparse_moe.experts.0.w1",
56
+ "block_sparse_moe.experts.1.w1",
57
+ "block_sparse_moe.experts.2.w1",
58
+ "block_sparse_moe.experts.3.w1",
59
+ "block_sparse_moe.experts.4.w1",
60
+ "block_sparse_moe.experts.5.w1",
61
+ "block_sparse_moe.experts.6.w1",
62
+ "block_sparse_moe.experts.7.w1",
63
+ "block_sparse_moe.experts.0.w3",
64
+ "block_sparse_moe.experts.1.w3",
65
+ "block_sparse_moe.experts.2.w3",
66
+ "block_sparse_moe.experts.3.w3",
67
+ "block_sparse_moe.experts.4.w3",
68
+ "block_sparse_moe.experts.5.w3",
69
+ "block_sparse_moe.experts.6.w3",
70
+ "block_sparse_moe.experts.7.w3"
71
+ ],
72
+ [
73
+ "block_sparse_moe.experts.0.w2",
74
+ "block_sparse_moe.experts.1.w2",
75
+ "block_sparse_moe.experts.2.w2",
76
+ "block_sparse_moe.experts.3.w2",
77
+ "block_sparse_moe.experts.4.w2",
78
+ "block_sparse_moe.experts.5.w2",
79
+ "block_sparse_moe.experts.6.w2",
80
+ "block_sparse_moe.experts.7.w2"
81
+ ]
82
+ ]
83
+ }
84
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:363252925b72fd196dbe5ea996b66965a180994a5160aaa85a934070cfdd4cc4
3
+ size 18496187648
quantize_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": -1,
4
+ "damp_percent": 0.1,
5
+ "desc_act": true,
6
+ "static_groups": false,
7
+ "sym": true,
8
+ "true_sequential": true,
9
+ "model_name_or_path": null,
10
+ "model_file_base_name": "model"
11
+ }
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
+ "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 %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "<s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": true
43
+ }