Severian commited on
Commit
d90ad14
1 Parent(s): ef7ba55

Upload 15 files

Browse files
config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 32000,
3
+ "max_position_embeddings": 32768,
4
+ "hidden_size": 4096,
5
+ "intermediate_size": 14336,
6
+ "num_hidden_layers": 32,
7
+ "num_attention_heads": 32,
8
+ "sliding_window": null,
9
+ "num_key_value_heads": 8,
10
+ "hidden_act": "silu",
11
+ "initializer_range": 0.02,
12
+ "rms_norm_eps": 1e-05,
13
+ "use_cache": true,
14
+ "rope_theta": 10000.0,
15
+ "attention_dropout": 0.0,
16
+ "num_experts_per_tok": 2,
17
+ "num_local_experts": 4,
18
+ "output_router_logits": false,
19
+ "router_aux_loss_coef": 0.001,
20
+ "return_dict": true,
21
+ "output_hidden_states": false,
22
+ "output_attentions": false,
23
+ "torchscript": false,
24
+ "torch_dtype": "bfloat16",
25
+ "use_bfloat16": false,
26
+ "tf_legacy_loss": false,
27
+ "pruned_heads": {},
28
+ "tie_word_embeddings": false,
29
+ "chunk_size_feed_forward": 0,
30
+ "is_encoder_decoder": false,
31
+ "is_decoder": false,
32
+ "cross_attention_hidden_size": null,
33
+ "add_cross_attention": false,
34
+ "tie_encoder_decoder": false,
35
+ "max_length": 20,
36
+ "min_length": 0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "num_beams": 1,
40
+ "num_beam_groups": 1,
41
+ "diversity_penalty": 0.0,
42
+ "temperature": 1.0,
43
+ "top_k": 50,
44
+ "top_p": 1.0,
45
+ "typical_p": 1.0,
46
+ "repetition_penalty": 1.0,
47
+ "length_penalty": 1.0,
48
+ "no_repeat_ngram_size": 0,
49
+ "encoder_no_repeat_ngram_size": 0,
50
+ "bad_words_ids": null,
51
+ "num_return_sequences": 1,
52
+ "output_scores": false,
53
+ "return_dict_in_generate": false,
54
+ "forced_bos_token_id": null,
55
+ "forced_eos_token_id": null,
56
+ "remove_invalid_values": false,
57
+ "exponential_decay_length_penalty": null,
58
+ "suppress_tokens": null,
59
+ "begin_suppress_tokens": null,
60
+ "architectures": [
61
+ "MixtralForCausalLM"
62
+ ],
63
+ "finetuning_task": null,
64
+ "id2label": {
65
+ "0": "LABEL_0",
66
+ "1": "LABEL_1"
67
+ },
68
+ "label2id": {
69
+ "LABEL_0": 0,
70
+ "LABEL_1": 1
71
+ },
72
+ "tokenizer_class": null,
73
+ "prefix": null,
74
+ "bos_token_id": 1,
75
+ "pad_token_id": 2,
76
+ "eos_token_id": 2,
77
+ "sep_token_id": null,
78
+ "decoder_start_token_id": null,
79
+ "task_specific_params": null,
80
+ "problem_type": null,
81
+ "_name_or_path": "/Users/anima/.cache/huggingface/hub/models--MaziyarPanahi--Bioxtral-4x7B-v0.1/snapshots/d0f47005d5b5b925e8a9de21d311ce278cf57eb7",
82
+ "transformers_version": "4.37.2",
83
+ "model_type": "mixtral",
84
+ "unsloth_version": "2024.1"
85
+ }
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1950aff672468be73fc50237f150a1e5adc7a2c26ed1f82313cf9aa112b1c361
3
+ size 5295497337
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b066ab5959967eb50fbb734e2f1cce44f377e2deca8e10b0b2f46343f0a7a4e
3
+ size 5301755733
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a2b03d2d1e220c64b616ab38d39eb6659103e124d358e0ab2f7e913a4a4a7d0
3
+ size 5268251144
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc22036db979a05cd9e8e972dcbbe6a84b0c5e0bceeb3f58a3d8fec41992792f
3
+ size 5352104403
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c257149e5b58ced1586e0b2c795530c5680f4720c41da8414b03b489ef4f0be
3
+ size 5335343229
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e615c1d6f4d1d022b2a747c464a82b53e39a864173ee5d9e5c8eaf2d6477c109
3
+ size 5268251188
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6ef2b17a0b307be95da718b6ffd12b84458650ca67ec990c3ecc363bafbf704
3
+ size 5301755799
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c8c2dff5fd01dd967431e2b83f9a8a9c391bcb6c90ba5cb2c66d09ab1047dd1
3
+ size 5268251178
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:941fc1b34be18f116ba45815af1ab0d442bb8aa6bf67ee1ee2622ad9d0c465f6
3
+ size 5301755795
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f54cb5aa86c85b9188e82ed37e90a1575636a028f0b99f46e3e2a4e0bbfd17
3
+ size 614490900
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": "<s>",
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
39
+ "max_length": null,
40
+ "model_max_length": 255,
41
+ "pad_to_multiple_of": null,
42
+ "pad_token": "<s>",
43
+ "pad_token_type_id": 0,
44
+ "padding_side": "left",
45
+ "sp_model_kwargs": {},
46
+ "spaces_between_special_tokens": false,
47
+ "tokenizer_class": "LlamaTokenizer",
48
+ "unk_token": "<unk>",
49
+ "use_default_system_prompt": true
50
+ }