TheBloke commited on
Commit
06b90cc
1 Parent(s): 47992ab

GPTQ model commit

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<sep>": 32002,
3
+ "<|end_of_turn|>": 32000,
4
+ "<|pad_0|>": 32001
5
+ }
config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/process/perlthoughts_starling-lm-alpha-8x7b-moe/source",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 32000,
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
+ "pad_token_id": 0,
22
+ "pretraining_tp": 1,
23
+ "quantization_config": {
24
+ "batch_size": 1,
25
+ "bits": 4,
26
+ "block_name_to_quantize": null,
27
+ "cache_block_outputs": true,
28
+ "damp_percent": 0.1,
29
+ "desc_act": true,
30
+ "exllama_config": {
31
+ "version": 1
32
+ },
33
+ "group_size": -1,
34
+ "max_input_length": null,
35
+ "model_seqlen": null,
36
+ "module_name_preceding_first_block": null,
37
+ "modules_in_block_to_quantize": [
38
+ [
39
+ "self_attn.k_proj",
40
+ "self_attn.v_proj",
41
+ "self_attn.q_proj"
42
+ ],
43
+ [
44
+ "self_attn.o_proj"
45
+ ],
46
+ [
47
+ "block_sparse_moe.experts.0.w1",
48
+ "block_sparse_moe.experts.1.w1",
49
+ "block_sparse_moe.experts.2.w1",
50
+ "block_sparse_moe.experts.3.w1",
51
+ "block_sparse_moe.experts.4.w1",
52
+ "block_sparse_moe.experts.5.w1",
53
+ "block_sparse_moe.experts.6.w1",
54
+ "block_sparse_moe.experts.7.w1",
55
+ "block_sparse_moe.experts.0.w3",
56
+ "block_sparse_moe.experts.1.w3",
57
+ "block_sparse_moe.experts.2.w3",
58
+ "block_sparse_moe.experts.3.w3",
59
+ "block_sparse_moe.experts.4.w3",
60
+ "block_sparse_moe.experts.5.w3",
61
+ "block_sparse_moe.experts.6.w3",
62
+ "block_sparse_moe.experts.7.w3"
63
+ ],
64
+ [
65
+ "block_sparse_moe.experts.0.w2",
66
+ "block_sparse_moe.experts.1.w2",
67
+ "block_sparse_moe.experts.2.w2",
68
+ "block_sparse_moe.experts.3.w2",
69
+ "block_sparse_moe.experts.4.w2",
70
+ "block_sparse_moe.experts.5.w2",
71
+ "block_sparse_moe.experts.6.w2",
72
+ "block_sparse_moe.experts.7.w2"
73
+ ]
74
+ ],
75
+ "pad_token_id": null,
76
+ "quant_method": "gptq",
77
+ "sym": true,
78
+ "tokenizer": null,
79
+ "true_sequential": true,
80
+ "use_cuda_fp16": false,
81
+ "use_exllama": true
82
+ },
83
+ "rms_norm_eps": 1e-05,
84
+ "rope_theta": 10000.0,
85
+ "router_aux_loss_coef": 0.001,
86
+ "sliding_window": 8192,
87
+ "tie_word_embeddings": false,
88
+ "torch_dtype": "bfloat16",
89
+ "transformers_version": "4.37.0.dev0",
90
+ "use_cache": true,
91
+ "vocab_size": 32002
92
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.37.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb0b0dfaeab1aafdfa2579b7b1497ff0305884e177fa73f5526b81f2b421ef61
3
+ size 23811583776
quantize_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": -1,
4
+ "damp_percent": 0.1,
5
+ "desc_act": true,
6
+ "sym": true,
7
+ "true_sequential": true
8
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|end_of_turn|>",
4
+ "<|pad_0|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|end_of_turn|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": "<s>",
21
+ "sep_token": "<sep>",
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 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|end_of_turn|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|pad_0|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<sep>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<|end_of_turn|>",
56
+ "<|pad_0|>"
57
+ ],
58
+ "bos_token": "<s>",
59
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
60
+ "clean_up_tokenization_spaces": false,
61
+ "eos_token": "<|end_of_turn|>",
62
+ "legacy": true,
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "<s>",
65
+ "sep_token": "<sep>",
66
+ "sp_model_kwargs": {},
67
+ "spaces_between_special_tokens": false,
68
+ "tokenizer_class": "LlamaTokenizer",
69
+ "unk_token": "<unk>",
70
+ "use_default_system_prompt": true
71
+ }