AntonV HF Staff commited on
Commit
b2b95e2
·
1 Parent(s): e5cf08a

v5 config version

Browse files
Files changed (1) hide show
  1. config.json +17 -53
config.json CHANGED
@@ -1,61 +1,25 @@
1
  {
2
- "activation_function": "swiglu",
3
- "architectures": [
4
- "NomicBertModel"
5
- ],
6
- "attn_pdrop": 0.0,
7
- "auto_map": {
8
- "AutoConfig": "nomic-ai/nomic-bert-2048--configuration_hf_nomic_bert.NomicBertConfig",
9
- "AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
10
- "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining",
11
- "AutoModelForSequenceClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForSequenceClassification",
12
- "AutoModelForMultipleChoice": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForMultipleChoice",
13
- "AutoModelForQuestionAnswering": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForQuestionAnswering",
14
- "AutoModelForTokenClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForTokenClassification"
15
- },
16
  "bos_token_id": null,
17
- "causal": false,
18
- "dense_seq_output": true,
19
- "embd_pdrop": 0.0,
20
  "eos_token_id": null,
21
- "fused_bias_fc": true,
22
- "fused_dropout_add_ln": true,
 
 
23
  "initializer_range": 0.02,
24
- "layer_norm_epsilon": 1e-12,
25
- "max_trained_positions": 2048,
26
- "mlp_fc1_bias": false,
27
- "mlp_fc2_bias": false,
28
  "model_type": "nomic_bert",
29
- "n_embd": 768,
30
- "n_head": 12,
31
- "n_inner": 3072,
32
- "n_layer": 12,
33
- "n_positions": 8192,
34
- "pad_vocab_size_multiple": 64,
35
- "parallel_block": false,
36
- "parallel_block_tied_norm": false,
37
- "prenorm": false,
38
- "qkv_proj_bias": false,
39
- "reorder_and_upcast_attn": false,
40
- "resid_pdrop": 0.0,
41
- "rotary_emb_base": 1000,
42
- "rotary_emb_fraction": 1.0,
43
- "rotary_emb_interleaved": false,
44
- "rotary_emb_scale_base": null,
45
- "rotary_scaling_factor": null,
46
- "scale_attn_by_inverse_layer_idx": false,
47
- "scale_attn_weights": true,
48
- "summary_activation": null,
49
- "summary_first_dropout": 0.0,
50
- "summary_proj_to_labels": true,
51
- "summary_type": "cls_index",
52
- "summary_use_proj": true,
53
- "torch_dtype": "float32",
54
- "transformers_version": "4.37.2",
55
  "type_vocab_size": 2,
56
- "use_cache": true,
57
- "use_flash_attn": true,
58
- "use_rms_norm": false,
59
- "use_xentropy": true,
60
  "vocab_size": 30528
61
  }
 
1
  {
2
+ "attention_probs_dropout_prob": 0.1,
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token_id": null,
4
+ "classifier_dropout": null,
 
 
5
  "eos_token_id": null,
6
+ "head_dim": 64,
7
+ "hidden_act": "silu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 2048,
 
14
  "model_type": "nomic_bert",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "rope_parameters": {
19
+ "rope_theta": 1000.0,
20
+ "rope_type": "default"
21
+ },
22
+ "transformers_version": "5.3.0.dev0",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "type_vocab_size": 2,
 
 
 
 
24
  "vocab_size": 30528
25
  }