comaniac commited on
Commit
2fe0104
1 Parent(s): c9bb3ce

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mixtral-8x7B-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": 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
+ "quantization_config": {
22
+ "activation_scheme": "static",
23
+ "ignored_layers": [
24
+ "model.layers.25.block_sparse_moe.gate",
25
+ "model.layers.2.block_sparse_moe.gate",
26
+ "model.layers.4.block_sparse_moe.gate",
27
+ "model.layers.26.block_sparse_moe.gate",
28
+ "model.layers.27.block_sparse_moe.gate",
29
+ "model.layers.20.block_sparse_moe.gate",
30
+ "model.layers.1.block_sparse_moe.gate",
31
+ "model.layers.30.block_sparse_moe.gate",
32
+ "model.layers.0.block_sparse_moe.gate",
33
+ "model.layers.5.block_sparse_moe.gate",
34
+ "model.layers.31.block_sparse_moe.gate",
35
+ "model.layers.12.block_sparse_moe.gate",
36
+ "model.layers.10.block_sparse_moe.gate",
37
+ "model.layers.19.block_sparse_moe.gate",
38
+ "model.layers.13.block_sparse_moe.gate",
39
+ "model.layers.24.block_sparse_moe.gate",
40
+ "model.layers.28.block_sparse_moe.gate",
41
+ "lm_head",
42
+ "model.layers.6.block_sparse_moe.gate",
43
+ "model.layers.15.block_sparse_moe.gate",
44
+ "model.layers.16.block_sparse_moe.gate",
45
+ "model.layers.17.block_sparse_moe.gate",
46
+ "model.layers.23.block_sparse_moe.gate",
47
+ "model.layers.7.block_sparse_moe.gate",
48
+ "model.layers.11.block_sparse_moe.gate",
49
+ "model.layers.22.block_sparse_moe.gate",
50
+ "model.layers.18.block_sparse_moe.gate",
51
+ "model.layers.29.block_sparse_moe.gate",
52
+ "model.layers.9.block_sparse_moe.gate",
53
+ "model.layers.21.block_sparse_moe.gate",
54
+ "model.layers.3.block_sparse_moe.gate",
55
+ "model.layers.8.block_sparse_moe.gate",
56
+ "model.layers.14.block_sparse_moe.gate"
57
+ ],
58
+ "quant_method": "fp8"
59
+ },
60
+ "rms_norm_eps": 1e-05,
61
+ "rope_theta": 1000000.0,
62
+ "router_aux_loss_coef": 0.02,
63
+ "router_jitter_noise": 0.0,
64
+ "sliding_window": null,
65
+ "tie_word_embeddings": false,
66
+ "torch_dtype": "bfloat16",
67
+ "transformers_version": "4.40.2",
68
+ "use_cache": true,
69
+ "vocab_size": 32000
70
+ }
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-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:007fc67953da654f6ede0cc18f72f528539310a6b63853bdc3aeb041e9e8022a
3
+ size 4951721496
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef45eed75005e9de217ae2446ef80570c5649352f44ff71838937e798138d70
3
+ size 4999891048
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8329698f5684785fcdfe576faf55cd092e45f216b0dc567bdafa3870fc265691
3
+ size 4983197024
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6624d39a8c82911e3a90c300631a953dbac269e3890264a6fc25cfbb4172e4ab
3
+ size 4999891336
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a2bdde20d5a851d0e4689990a74ba57b561842bd2a42a8cb3b73644a7821a0
3
+ size 4999907944
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15440fbdf1a10971d4e1004c6b387997428248d68883125e90cecfbfa146d36b
3
+ size 4983180712
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b7680fccd1e281c44759ef4f9fcf3ffbd1dcc854c6168b351fc03f50d21c78f
3
+ size 4999891336
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b85413021fd77477ed468f49141fdc41d2463d10f2239a321e4d5344d4715d23
3
+ size 4983197312
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666099e7a00e3846043c5aadb00c447839fdac6ae70a9c70b6a3695c4aa28e9a
3
+ size 4999891336
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ff168f30fdaf9649789a3334da9a40ad16e5e9378bf73a668840da1a08c7892
3
+ size 2065814216
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": 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
+ }