Hugging Face's logo

zjunlp
/
InstructCell-chat

PyTorch
instructcell
Model card Files Community
ZJU-Fangyin commited on
Commit
35108e1
·
1 Parent(s): 0a2321d

Update the configuration

Browse files
Files changed (4) hide show
  1. README.md +0 -3
  2. config.json +83 -67
  3. generation_config.json +4 -0
  4. pytorch_model.bin +2 -2
README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
config.json CHANGED
@@ -1,76 +1,92 @@
1
  {
2
- "_name_or_path": "../t5-base",
3
  "architectures": [
4
- "T5ForConditionalGeneration"
5
  ],
6
- "classifier_dropout": 0.0,
7
- "d_ff": 3072,
8
- "d_kv": 64,
9
- "d_model": 768,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "relu",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "relu",
15
- "ignore_index": -100,
16
- "initializer_factor": 1.0,
17
- "is_encoder_decoder": true,
18
- "is_gated_act": false,
19
- "layer_norm_epsilon": 1e-06,
20
- "model_type": "t5",
21
- "n_positions": 512,
22
- "num_decoder_layers": 12,
23
- "num_heads": 12,
24
- "num_layers": 12,
25
- "num_signal_tokens": 1,
26
- "output_past": true,
27
- "pad_token_id": 0,
28
- "relative_attention_max_distance": 128,
29
- "relative_attention_num_buckets": 32,
30
- "special_tokens_dict": {
31
- "end_tag": "</CELL>",
32
- "placeholder": "<CELL0>",
33
- "signal_tokens": [
34
- "<CELL1>"
35
  ],
36
- "start_tag": "<CELL>"
37
- },
38
- "special_tokens_index_dict": {
39
- "end_tag": 32101,
40
- "first_signal_token": 32103,
41
- "placeholder": 32102,
42
- "start_tag": 32100
43
- },
44
- "task_specific_params": {
45
- "summarization": {
46
- "early_stopping": true,
47
- "length_penalty": 2.0,
48
- "max_length": 200,
49
- "min_length": 30,
50
- "no_repeat_ngram_size": 3,
51
- "num_beams": 4,
52
- "prefix": "summarize: "
 
53
  },
54
- "translation_en_to_de": {
55
- "early_stopping": true,
56
- "max_length": 300,
57
- "num_beams": 4,
58
- "prefix": "translate English to German: "
59
  },
60
- "translation_en_to_fr": {
61
- "early_stopping": true,
62
- "max_length": 300,
63
- "num_beams": 4,
64
- "prefix": "translate English to French: "
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
  },
66
- "translation_en_to_ro": {
67
- "early_stopping": true,
68
- "max_length": 300,
69
- "num_beams": 4,
70
- "prefix": "translate English to Romanian: "
71
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
  },
73
- "transformers_version": "4.33.3",
74
- "use_cache": true,
75
- "vocab_size": 32112
 
 
 
76
  }
 
1
  {
 
2
  "architectures": [
3
+ "InstructCell"
4
  ],
5
+ "base_model_config": {
6
+ "architectures": [
7
+ "T5ForConditionalGeneration"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  ],
9
+ "d_ff": 3072,
10
+ "d_model": 768,
11
+ "decoder_start_token_id": 0,
12
+ "ignore_index": null,
13
+ "model_type": "t5",
14
+ "n_positions": 512,
15
+ "num_decoder_layers": 12,
16
+ "num_heads": 12,
17
+ "num_layers": 12,
18
+ "num_signal_tokens": 1,
19
+ "output_past": true,
20
+ "special_tokens_dict": {
21
+ "end_tag": "</CELL>",
22
+ "placeholder": "<CELL0>",
23
+ "signal_tokens": [
24
+ "<CELL1>"
25
+ ],
26
+ "start_tag": "<CELL>"
27
  },
28
+ "special_tokens_index_dict": {
29
+ "end_tag": 32101,
30
+ "first_signal_token": 32103,
31
+ "placeholder": 32102,
32
+ "start_tag": 32100
33
  },
34
+ "task_specific_params": {
35
+ "summarization": {
36
+ "early_stopping": true,
37
+ "length_penalty": 2.0,
38
+ "max_length": 200,
39
+ "min_length": 30,
40
+ "no_repeat_ngram_size": 3,
41
+ "num_beams": 4,
42
+ "prefix": "summarize: "
43
+ },
44
+ "translation_en_to_de": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to German: "
49
+ },
50
+ "translation_en_to_fr": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to French: "
55
+ },
56
+ "translation_en_to_ro": {
57
+ "early_stopping": true,
58
+ "max_length": 300,
59
+ "num_beams": 4,
60
+ "prefix": "translate English to Romanian: "
61
+ }
62
  },
63
+ "vocab_size": 32112
64
+ },
65
+ "feature_decoder_config": {
66
+ "adaptive_library": true,
67
+ "condition_input_dim": 256,
68
+ "dropout_rate": 0.1,
69
+ "log_variational": true,
70
+ "n_hidden": 1024,
71
+ "n_latent": 256,
72
+ "n_layers": 4,
73
+ "use_batch_norm": "none",
74
+ "use_layer_norm": "both"
75
+ },
76
+ "feature_encoder_config": {
77
+ "count_dim": 18961,
78
+ "cross_attention_frequency": 1,
79
+ "hidden_dropout_prob": 0.1,
80
+ "is_q_former_encoder": true,
81
+ "num_blocks": 3,
82
+ "num_hidden_layers": 4,
83
+ "num_key_value_tokens": 6,
84
+ "num_query_tokens": 8
85
  },
86
+ "log_variational": true,
87
+ "model_type": "instructcell",
88
+ "normalize_total": true,
89
+ "tokenizer_use_fast": false,
90
+ "torch_dtype": "float32",
91
+ "transformers_version": "4.33.3"
92
  }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.33.3"
4
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fae1a0d72fb3b65b7089db60606581d17a32375bca4af2618487e405a6663748
3
- size 1983486457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb61d751a0e0ff3e9b8c2aca089275d2dacafffb37724167e339d88dc3dd723a
3
+ size 1983432121