Hugging Face's logo

JingzeShi
/
Mixtral-7B-v0.1

Text Generation
Transformers
Safetensors
mixtral
text-generation-inference
Model card Files
xet
Community
JingzeShi commited on
Commit
b896e90
·
verified ·
1 Parent(s): 3cc32c6

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. .ipynb_checkpoints/config-checkpoint.json +87 -0
  2. config.json +87 -0
  3. model.safetensors +3 -0
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1000000.0,
15
+ "attention_dropout": 0.0,
16
+ "head_dim": 128,
17
+ "num_experts_per_tok": 2,
18
+ "num_local_experts": 8,
19
+ "output_router_logits": false,
20
+ "router_aux_loss_coef": 0.02,
21
+ "router_jitter_noise": 0.0,
22
+ "return_dict": true,
23
+ "output_hidden_states": false,
24
+ "output_attentions": false,
25
+ "torchscript": false,
26
+ "torch_dtype": "bfloat16",
27
+ "use_bfloat16": false,
28
+ "tf_legacy_loss": false,
29
+ "pruned_heads": {},
30
+ "tie_word_embeddings": false,
31
+ "chunk_size_feed_forward": 0,
32
+ "is_encoder_decoder": false,
33
+ "is_decoder": false,
34
+ "cross_attention_hidden_size": null,
35
+ "add_cross_attention": false,
36
+ "tie_encoder_decoder": false,
37
+ "max_length": 20,
38
+ "min_length": 0,
39
+ "do_sample": false,
40
+ "early_stopping": false,
41
+ "num_beams": 1,
42
+ "num_beam_groups": 1,
43
+ "diversity_penalty": 0.0,
44
+ "temperature": 1.0,
45
+ "top_k": 50,
46
+ "top_p": 1.0,
47
+ "typical_p": 1.0,
48
+ "repetition_penalty": 1.0,
49
+ "length_penalty": 1.0,
50
+ "no_repeat_ngram_size": 0,
51
+ "encoder_no_repeat_ngram_size": 0,
52
+ "bad_words_ids": null,
53
+ "num_return_sequences": 1,
54
+ "output_scores": false,
55
+ "return_dict_in_generate": false,
56
+ "forced_bos_token_id": null,
57
+ "forced_eos_token_id": null,
58
+ "remove_invalid_values": false,
59
+ "exponential_decay_length_penalty": null,
60
+ "suppress_tokens": null,
61
+ "begin_suppress_tokens": null,
62
+ "architectures": [
63
+ "MixtralForCausalLM"
64
+ ],
65
+ "finetuning_task": null,
66
+ "id2label": {
67
+ "0": "LABEL_0",
68
+ "1": "LABEL_1"
69
+ },
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1
73
+ },
74
+ "tokenizer_class": null,
75
+ "prefix": null,
76
+ "bos_token_id": 1,
77
+ "pad_token_id": null,
78
+ "eos_token_id": 2,
79
+ "sep_token_id": null,
80
+ "decoder_start_token_id": null,
81
+ "task_specific_params": null,
82
+ "problem_type": null,
83
+ "_name_or_path": "",
84
+ "_attn_implementation_autoset": false,
85
+ "transformers_version": "4.49.0",
86
+ "model_type": "mixtral"
87
+ }
config.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1000000.0,
15
+ "attention_dropout": 0.0,
16
+ "head_dim": 128,
17
+ "num_experts_per_tok": 2,
18
+ "num_local_experts": 8,
19
+ "output_router_logits": false,
20
+ "router_aux_loss_coef": 0.02,
21
+ "router_jitter_noise": 0.0,
22
+ "return_dict": true,
23
+ "output_hidden_states": false,
24
+ "output_attentions": false,
25
+ "torchscript": false,
26
+ "torch_dtype": "bfloat16",
27
+ "use_bfloat16": false,
28
+ "tf_legacy_loss": false,
29
+ "pruned_heads": {},
30
+ "tie_word_embeddings": false,
31
+ "chunk_size_feed_forward": 0,
32
+ "is_encoder_decoder": false,
33
+ "is_decoder": false,
34
+ "cross_attention_hidden_size": null,
35
+ "add_cross_attention": false,
36
+ "tie_encoder_decoder": false,
37
+ "max_length": 20,
38
+ "min_length": 0,
39
+ "do_sample": false,
40
+ "early_stopping": false,
41
+ "num_beams": 1,
42
+ "num_beam_groups": 1,
43
+ "diversity_penalty": 0.0,
44
+ "temperature": 1.0,
45
+ "top_k": 50,
46
+ "top_p": 1.0,
47
+ "typical_p": 1.0,
48
+ "repetition_penalty": 1.0,
49
+ "length_penalty": 1.0,
50
+ "no_repeat_ngram_size": 0,
51
+ "encoder_no_repeat_ngram_size": 0,
52
+ "bad_words_ids": null,
53
+ "num_return_sequences": 1,
54
+ "output_scores": false,
55
+ "return_dict_in_generate": false,
56
+ "forced_bos_token_id": null,
57
+ "forced_eos_token_id": null,
58
+ "remove_invalid_values": false,
59
+ "exponential_decay_length_penalty": null,
60
+ "suppress_tokens": null,
61
+ "begin_suppress_tokens": null,
62
+ "architectures": [
63
+ "MixtralForCausalLM"
64
+ ],
65
+ "finetuning_task": null,
66
+ "id2label": {
67
+ "0": "LABEL_0",
68
+ "1": "LABEL_1"
69
+ },
70
+ "label2id": {
71
+ "LABEL_0": 0,
72
+ "LABEL_1": 1
73
+ },
74
+ "tokenizer_class": null,
75
+ "prefix": null,
76
+ "bos_token_id": 1,
77
+ "pad_token_id": null,
78
+ "eos_token_id": 2,
79
+ "sep_token_id": null,
80
+ "decoder_start_token_id": null,
81
+ "task_specific_params": null,
82
+ "problem_type": null,
83
+ "_name_or_path": "",
84
+ "_attn_implementation_autoset": false,
85
+ "transformers_version": "4.49.0",
86
+ "model_type": "mixtral"
87
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e1c394706733134732d5353ce59635a0c4e7ec3e163602b078ce2662709d88
3
+ size 14485600992