louisbrulenaudet commited on
Commit
4394f49
1 Parent(s): a7af91a

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vocab_size": 32002,
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": false,
14
+ "rope_theta": 10000.0,
15
+ "attention_dropout": 0.0,
16
+ "num_experts_per_tok": 2,
17
+ "num_local_experts": 3,
18
+ "output_router_logits": false,
19
+ "router_aux_loss_coef": 0.001,
20
+ "router_jitter_noise": 0.0,
21
+ "return_dict": true,
22
+ "output_hidden_states": false,
23
+ "output_attentions": false,
24
+ "torchscript": false,
25
+ "torch_dtype": "float16",
26
+ "use_bfloat16": false,
27
+ "tf_legacy_loss": false,
28
+ "pruned_heads": {},
29
+ "tie_word_embeddings": false,
30
+ "chunk_size_feed_forward": 0,
31
+ "is_encoder_decoder": false,
32
+ "is_decoder": false,
33
+ "cross_attention_hidden_size": null,
34
+ "add_cross_attention": false,
35
+ "tie_encoder_decoder": false,
36
+ "max_length": 20,
37
+ "min_length": 0,
38
+ "do_sample": false,
39
+ "early_stopping": false,
40
+ "num_beams": 1,
41
+ "num_beam_groups": 1,
42
+ "diversity_penalty": 0.0,
43
+ "temperature": 1.0,
44
+ "top_k": 50,
45
+ "top_p": 1.0,
46
+ "typical_p": 1.0,
47
+ "repetition_penalty": 1.0,
48
+ "length_penalty": 1.0,
49
+ "no_repeat_ngram_size": 0,
50
+ "encoder_no_repeat_ngram_size": 0,
51
+ "bad_words_ids": null,
52
+ "num_return_sequences": 1,
53
+ "output_scores": false,
54
+ "return_dict_in_generate": false,
55
+ "forced_bos_token_id": null,
56
+ "forced_eos_token_id": null,
57
+ "remove_invalid_values": false,
58
+ "exponential_decay_length_penalty": null,
59
+ "suppress_tokens": null,
60
+ "begin_suppress_tokens": null,
61
+ "architectures": [
62
+ "MixtralForCausalLM"
63
+ ],
64
+ "finetuning_task": null,
65
+ "id2label": {
66
+ "0": "LABEL_0",
67
+ "1": "LABEL_1"
68
+ },
69
+ "label2id": {
70
+ "LABEL_0": 0,
71
+ "LABEL_1": 1
72
+ },
73
+ "tokenizer_class": null,
74
+ "prefix": null,
75
+ "bos_token_id": 1,
76
+ "pad_token_id": null,
77
+ "eos_token_id": 32000,
78
+ "sep_token_id": null,
79
+ "decoder_start_token_id": null,
80
+ "task_specific_params": null,
81
+ "problem_type": null,
82
+ "_name_or_path": "/home/jupyter/.cache/huggingface/hub/models--louisbrulenaudet--Pearl-3x7B/snapshots/63499a3e77b66d0709c15208720d48e89b4c1786",
83
+ "transformers_version": "4.43.4",
84
+ "model_type": "mixtral",
85
+ "quantization": {
86
+ "group_size": 64,
87
+ "bits": 4
88
+ }
89
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774e49f9ffd95fe62678d1fe8228cf9891824af4c1d074c77d7d8af37d925b17
3
+ size 5363400841
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53daac7a0a72dfeb479bc8a56fb9d02b6bfaa249137f94416aba8761ddfe579c
3
+ size 5241076229
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ }
46
+ },
47
+ "additional_special_tokens": [],
48
+ "bos_token": "<s>",
49
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "<|im_end|>",
52
+ "legacy": true,
53
+ "max_length": null,
54
+ "model_max_length": 1000000000000000019884624838656,
55
+ "pad_to_multiple_of": null,
56
+ "pad_token": "<s>",
57
+ "pad_token_type_id": 0,
58
+ "padding_side": "left",
59
+ "sp_model_kwargs": {},
60
+ "spaces_between_special_tokens": false,
61
+ "tokenizer_class": "LlamaTokenizer",
62
+ "trust_remote_code": false,
63
+ "unk_token": "<unk>",
64
+ "use_default_system_prompt": true,
65
+ "use_fast": true
66
+ }