orion-penner HF staff commited on
Commit
5844bf3
1 Parent(s): d16afdf

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -64,7 +64,8 @@
64
  ],
65
  "quant_method": "gptq",
66
  "sym": true,
67
- "true_sequential": true
 
68
  },
69
  "rms_norm_eps": 1e-05,
70
  "rope_theta": 1000000.0,
@@ -75,4 +76,4 @@
75
  "transformers_version": "4.38.0.dev0",
76
  "use_cache": true,
77
  "vocab_size": 32000
78
- }
 
64
  ],
65
  "quant_method": "gptq",
66
  "sym": true,
67
+ "true_sequential": true,
68
+ "disable_exllama": false
69
  },
70
  "rms_norm_eps": 1e-05,
71
  "rope_theta": 1000000.0,
 
76
  "transformers_version": "4.38.0.dev0",
77
  "use_cache": true,
78
  "vocab_size": 32000
79
+ }
quantize_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "dataset": "wikitext2",
4
+ "group_size": 128,
5
+ "damp_percent": 0.1,
6
+ "desc_act": false,
7
+ "sym": true,
8
+ "true_sequential": true,
9
+ "quant_method": "gptq",
10
+ "modules_in_block_to_quantize": [
11
+ [
12
+ "self_attn.k_proj",
13
+ "self_attn.v_proj",
14
+ "self_attn.q_proj"
15
+ ],
16
+ [
17
+ "self_attn.o_proj"
18
+ ],
19
+ [
20
+ "block_sparse_moe.experts.0.w1",
21
+ "block_sparse_moe.experts.1.w1",
22
+ "block_sparse_moe.experts.2.w1",
23
+ "block_sparse_moe.experts.3.w1",
24
+ "block_sparse_moe.experts.4.w1",
25
+ "block_sparse_moe.experts.5.w1",
26
+ "block_sparse_moe.experts.6.w1",
27
+ "block_sparse_moe.experts.7.w1",
28
+ "block_sparse_moe.experts.0.w3",
29
+ "block_sparse_moe.experts.1.w3",
30
+ "block_sparse_moe.experts.2.w3",
31
+ "block_sparse_moe.experts.3.w3",
32
+ "block_sparse_moe.experts.4.w3",
33
+ "block_sparse_moe.experts.5.w3",
34
+ "block_sparse_moe.experts.6.w3",
35
+ "block_sparse_moe.experts.7.w3"
36
+ ],
37
+ [
38
+ "block_sparse_moe.experts.0.w2",
39
+ "block_sparse_moe.experts.1.w2",
40
+ "block_sparse_moe.experts.2.w2",
41
+ "block_sparse_moe.experts.3.w2",
42
+ "block_sparse_moe.experts.4.w2",
43
+ "block_sparse_moe.experts.5.w2",
44
+ "block_sparse_moe.experts.6.w2",
45
+ "block_sparse_moe.experts.7.w2"
46
+ ]
47
+ ]
48
+ }
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.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": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
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
+ }