comaniac commited on
Commit
78b0674
1 Parent(s): bfaae04

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mixtral-8x22B-Instruct-v0.1",
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": 6144,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "max_position_embeddings": 65536,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 48,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 56,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "quantization_config": {
22
+ "activation_scheme": "static",
23
+ "ignored_layers": [
24
+ "model.layers.46.block_sparse_moe.gate",
25
+ "model.layers.54.block_sparse_moe.gate",
26
+ "model.layers.39.block_sparse_moe.gate",
27
+ "model.layers.8.block_sparse_moe.gate",
28
+ "model.layers.14.block_sparse_moe.gate",
29
+ "model.layers.12.block_sparse_moe.gate",
30
+ "model.layers.13.block_sparse_moe.gate",
31
+ "model.layers.5.block_sparse_moe.gate",
32
+ "model.layers.40.block_sparse_moe.gate",
33
+ "model.layers.31.block_sparse_moe.gate",
34
+ "model.layers.7.block_sparse_moe.gate",
35
+ "model.layers.28.block_sparse_moe.gate",
36
+ "model.layers.11.block_sparse_moe.gate",
37
+ "model.layers.25.block_sparse_moe.gate",
38
+ "model.layers.29.block_sparse_moe.gate",
39
+ "model.layers.37.block_sparse_moe.gate",
40
+ "model.layers.44.block_sparse_moe.gate",
41
+ "model.layers.50.block_sparse_moe.gate",
42
+ "model.layers.17.block_sparse_moe.gate",
43
+ "model.layers.26.block_sparse_moe.gate",
44
+ "model.layers.34.block_sparse_moe.gate",
45
+ "model.layers.42.block_sparse_moe.gate",
46
+ "model.layers.4.block_sparse_moe.gate",
47
+ "model.layers.36.block_sparse_moe.gate",
48
+ "model.layers.51.block_sparse_moe.gate",
49
+ "lm_head",
50
+ "model.layers.18.block_sparse_moe.gate",
51
+ "model.layers.43.block_sparse_moe.gate",
52
+ "model.layers.53.block_sparse_moe.gate",
53
+ "model.layers.35.block_sparse_moe.gate",
54
+ "model.layers.6.block_sparse_moe.gate",
55
+ "model.layers.15.block_sparse_moe.gate",
56
+ "model.layers.22.block_sparse_moe.gate",
57
+ "model.layers.0.block_sparse_moe.gate",
58
+ "model.layers.38.block_sparse_moe.gate",
59
+ "model.layers.48.block_sparse_moe.gate",
60
+ "model.layers.2.block_sparse_moe.gate",
61
+ "model.layers.41.block_sparse_moe.gate",
62
+ "model.layers.21.block_sparse_moe.gate",
63
+ "model.layers.20.block_sparse_moe.gate",
64
+ "model.layers.49.block_sparse_moe.gate",
65
+ "model.layers.10.block_sparse_moe.gate",
66
+ "model.layers.32.block_sparse_moe.gate",
67
+ "model.layers.33.block_sparse_moe.gate",
68
+ "model.layers.30.block_sparse_moe.gate",
69
+ "model.layers.19.block_sparse_moe.gate",
70
+ "model.layers.3.block_sparse_moe.gate",
71
+ "model.layers.55.block_sparse_moe.gate",
72
+ "model.layers.23.block_sparse_moe.gate",
73
+ "model.layers.9.block_sparse_moe.gate",
74
+ "model.layers.45.block_sparse_moe.gate",
75
+ "model.layers.47.block_sparse_moe.gate",
76
+ "model.layers.1.block_sparse_moe.gate",
77
+ "model.layers.27.block_sparse_moe.gate",
78
+ "model.layers.16.block_sparse_moe.gate",
79
+ "model.layers.52.block_sparse_moe.gate",
80
+ "model.layers.24.block_sparse_moe.gate"
81
+ ],
82
+ "quant_method": "fp8"
83
+ },
84
+ "rms_norm_eps": 1e-05,
85
+ "rope_theta": 1000000.0,
86
+ "router_aux_loss_coef": 0.001,
87
+ "router_jitter_noise": 0.0,
88
+ "sliding_window": null,
89
+ "tie_word_embeddings": false,
90
+ "torch_dtype": "bfloat16",
91
+ "transformers_version": "4.40.2",
92
+ "use_cache": true,
93
+ "vocab_size": 32768
94
+ }
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": "4.40.2"
6
+ }
model-00001-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feeaba3ba0deb90aba2acbaccf5b28a977cebfce7dbf0fb67a76fab44d88c488
3
+ size 4907575592
model-00002-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3923e8a719c3d167526e323eeccd6323ca23c91f6f54cc0dc63e0f8397ef39
3
+ size 4907601696
model-00003-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c4dbaf1ce89288820d47d9196ec615182ffae5c66c268d00a674c5d6aa8cfe9
3
+ size 4907601696
model-00004-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:003ea3e3e77a4a7dc43c295ff20d43de69a4f4990b443d0114a8bd790d9aab84
3
+ size 4907601696
model-00005-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094e6fdfec5187751d408e6cdc045b4d2b76959bea11c3ae209250a122add87f
3
+ size 4907601696
model-00006-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:855877733e628caf1adf139d1d89d39b4bcdc1bf4ea76726274b21881aee363a
3
+ size 4907601840
model-00007-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a038a3d3057defd6b800285886b6c6d07ecd7f2de2ff2c877ffa220b06580b08
3
+ size 4907601872
model-00008-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d877586f18dc6b3650e01040e2a19657907167978ee208bf55554935b13ddd
3
+ size 4907601872
model-00009-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b5a86bf12c7645378da6f06be87411e8d2ea3ebc906afd87907a952e0f4434
3
+ size 4907601872
model-00010-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571d39ce45753c3f9be50d6d937e1d64dbfc30252d610204606d380f6beaedb4
3
+ size 4907601872
model-00011-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f50942bcc52e0b281a70ce3eb7d027be54f80cf73a1fc5b36f309424304b091
3
+ size 4907601872
model-00012-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0315dc479d6b6c6f45fd3d6a5f7dab67551bf36a079d2384cbde29882fb9a953
3
+ size 4907601872
model-00013-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:accde5e3bf798993409a9bef942d4ee375b542d08c182bea19fd22680ba23d73
3
+ size 4907601872
model-00014-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8419aa3d77ec77892f2b1b51662b027749aaf7df1e8622b7330436b26c1aab49
3
+ size 4907601872
model-00015-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2497514b4bcef211e007543ffa675894289b8f2d426bd554dc3fbd839ea8c104
3
+ size 4907601872
model-00016-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ee41cfc59cce770f2601b5beb4db0d7a9678ed84f925ea0f3f3f87eb5b437c
3
+ size 4907601872
model-00017-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d4ace5412e5b6311349b4cb8dc724ac2044bbcd6289e56b8916941560cb71d5
3
+ size 4907601872
model-00018-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f1f6363fdfb16c0cfbd25996f23f7dd856673dec1c052bfcf2f45f9e3688d26
3
+ size 4907601872
model-00019-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df2418a9427e6247e9a34368653db7397b06ffa1b4fd6b94e36727593c45c66
3
+ size 4907601872
model-00020-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:355aff4469d95f814bf4a9e92bc68f2b3bc9c4af297fba73f61aecc267d712d7
3
+ size 4907601872
model-00021-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f623934d15eae85cb5631ea52f5aa127aad7f9a18f21379f498d0204615e13ec
3
+ size 4970418056
model-00022-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15c9144d9a86986371655249e099b64c1b69ca172cf1547b7a292f1ede0ce3cd
3
+ size 4995681968
model-00023-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaf13a3b6fe8df601db09a39ccbe68b9b9b6d15d106b28f4440674f66065ea3c
3
+ size 4970516472
model-00024-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa93e526e8f7ed83d42431a1c27e2874fda25918fb3a82333bf663762d9afb38
3
+ size 4907577080
model-00025-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61e96504cd25d35422cdfa4231249ba693c8d2cd0dcdd259f07c0db2cc7e5d51
3
+ size 4907601872
model-00026-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80dc37b86af2669be32126106111d005fb9e6f5f38d667ce0e84570c47e5268e
3
+ size 4907601872
model-00027-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5957e841f4ccebcfe394cbebcbfc2ee2ab9823324ec4295ec79f4918cbc2ef1d
3
+ size 4907601872
model-00028-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e037d15397af14dc64bca8b8fe6eb062e2060762e5dae23851c282ec8d9362de
3
+ size 4907601872
model-00029-of-00029.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d1cf3b2b2a07aad91cef048a6e6b0eb1fe879554db596d130d37984f9135be5
3
+ size 3410141544
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": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
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 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "[INST]",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "[/INST]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "[TOOL_CALLS]",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "[AVAILABLE_TOOLS]",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "[/AVAILABLE_TOOLS]",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "[TOOL_RESULTS]",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "[/TOOL_RESULTS]",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ }
85
+ },
86
+ "additional_special_tokens": [],
87
+ "bos_token": "<s>",
88
+ "chat_template": [
89
+ {
90
+ "name": "default",
91
+ "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 %}"
92
+ },
93
+ {
94
+ "name": "tool_use",
95
+ "template": "{{bos_token}}{% set user_messages = messages | selectattr('role', 'equalto', 'user') | list %}{% for message in messages %}{% if message['role'] == 'user' %}{% if message == user_messages[-1] %}{% if tools %}{{'[AVAILABLE_TOOLS]'+ tools|string + '[/AVAILABLE_TOOLS]'}}{% endif %}{{ '[INST]' + message['content'] + '[/INST]' }}{% else %}{{ '[INST]' + message['content'] + '[/INST]' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + ' ' + eos_token}}{% elif message['role'] == 'tool_results' %}{{'[TOOL_RESULTS]' + message['content']|string + '[/TOOL_RESULTS]'}}{% elif message['role'] == 'tool_calls' %}{{'[TOOL_CALLS]' + message['content']|string + eos_token}}{% endif %}{% endfor %}"
96
+ }
97
+ ],
98
+ "clean_up_tokenization_spaces": false,
99
+ "eos_token": "</s>",
100
+ "legacy": true,
101
+ "model_max_length": 1000000000000000019884624838656,
102
+ "pad_token": null,
103
+ "sp_model_kwargs": {},
104
+ "spaces_between_special_tokens": false,
105
+ "tokenizer_class": "LlamaTokenizer",
106
+ "unk_token": "<unk>",
107
+ "use_default_system_prompt": false
108
+ }