TheBloke commited on
Commit
54fa0dc
1 Parent(s): 70acf5c

GPTQ model commit

Browse files
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/process/grimulkan_goliath-longlora-120b-rope8-32k-fp16/source",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
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": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 4096,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 137,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "batch_size": 1,
23
+ "bits": 4,
24
+ "block_name_to_quantize": null,
25
+ "cache_block_outputs": true,
26
+ "damp_percent": 0.1,
27
+ "desc_act": true,
28
+ "exllama_config": {
29
+ "version": 1
30
+ },
31
+ "group_size": 128,
32
+ "max_input_length": null,
33
+ "model_seqlen": null,
34
+ "module_name_preceding_first_block": null,
35
+ "modules_in_block_to_quantize": [
36
+ [
37
+ "self_attn.k_proj",
38
+ "self_attn.v_proj",
39
+ "self_attn.q_proj"
40
+ ],
41
+ [
42
+ "self_attn.o_proj"
43
+ ],
44
+ [
45
+ "mlp.up_proj",
46
+ "mlp.gate_proj"
47
+ ],
48
+ [
49
+ "mlp.down_proj"
50
+ ]
51
+ ],
52
+ "pad_token_id": null,
53
+ "quant_method": "gptq",
54
+ "sym": true,
55
+ "tokenizer": null,
56
+ "true_sequential": true,
57
+ "use_cuda_fp16": false,
58
+ "use_exllama": true
59
+ },
60
+ "rms_norm_eps": 1e-05,
61
+ "rope_scaling": {
62
+ "factor": 8.0,
63
+ "type": "linear"
64
+ },
65
+ "rope_theta": 10000.0,
66
+ "tie_word_embeddings": false,
67
+ "torch_dtype": "float16",
68
+ "transformers_version": "4.37.0.dev0",
69
+ "use_cache": true,
70
+ "vocab_size": 32000
71
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.37.0.dev0"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d5be2b6a1bbbe0b43bf0d3c441185cd27e3e88da01784ad54da63909cd96147
3
+ size 48912250480
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c52ccb959718aa0351d65f7916f285bf6524451b9fe76a9dd3897cedc29b2f3
3
+ size 13107770280
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
quantize_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.1,
5
+ "desc_act": true,
6
+ "sym": true,
7
+ "true_sequential": true
8
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "unk_token": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
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
+ "clean_up_tokenization_spaces": false,
37
+ "eos_token": "</s>",
38
+ "legacy": false,
39
+ "model_max_length": 32768,
40
+ "pad_token": "<unk>",
41
+ "padding_side": "right",
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
+ }