Hugging Face's logo

nomic-ai
/
nomic-embed-text-v1.5

Sentence Similarity
sentence-transformers
ONNX
Safetensors
Transformers
Transformers.js
English
nomic_bert
feature-extraction
mteb
custom_code
Eval Results (legacy)
Eval Results
text-embeddings-inference
Model card Files
xet
 Community
61
AntonV HF Staff commited on
Commit
e8134cb
·
1 Parent(s): b2b95e2

franken config + fix st

Browse files
Files changed (2) hide show
  1. config.json +54 -2
  2. sentence_bert_config.json +1 -4
config.json CHANGED
@@ -1,25 +1,77 @@
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
  }
 
1
  {
2
+ "activation_function": "swiglu",
3
+ "architectures": [
4
+ "NomicBertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "attn_pdrop": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "nomic-ai/nomic-bert-2048--configuration_hf_nomic_bert.NomicBertConfig",
10
+ "AutoModel": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertModel",
11
+ "AutoModelForMaskedLM": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForPreTraining",
12
+ "AutoModelForSequenceClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForSequenceClassification",
13
+ "AutoModelForMultipleChoice": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForMultipleChoice",
14
+ "AutoModelForQuestionAnswering": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForQuestionAnswering",
15
+ "AutoModelForTokenClassification": "nomic-ai/nomic-bert-2048--modeling_hf_nomic_bert.NomicBertForTokenClassification"
16
+ },
17
  "bos_token_id": null,
18
+ "causal": false,
19
  "classifier_dropout": null,
20
+ "dense_seq_output": true,
21
+ "embd_pdrop": 0.0,
22
  "eos_token_id": null,
23
+ "fused_bias_fc": true,
24
+ "fused_dropout_add_ln": true,
25
  "head_dim": 64,
26
  "hidden_act": "silu",
27
+ "hidden_dropout_prob": 0.0,
28
  "hidden_size": 768,
29
  "initializer_range": 0.02,
30
  "intermediate_size": 3072,
31
+ "layer_norm_epsilon": 1e-12,
32
  "layer_norm_eps": 1e-12,
33
  "max_position_embeddings": 2048,
34
+ "max_trained_positions": 2048,
35
+ "mlp_fc1_bias": false,
36
+ "mlp_fc2_bias": false,
37
  "model_type": "nomic_bert",
38
+ "n_embd": 768,
39
+ "n_head": 12,
40
+ "n_inner": 3072,
41
+ "n_layer": 12,
42
+ "n_positions": 8192,
43
  "num_attention_heads": 12,
44
  "num_hidden_layers": 12,
45
  "pad_token_id": 0,
46
+ "pad_vocab_size_multiple": 64,
47
+ "parallel_block": false,
48
+ "parallel_block_tied_norm": false,
49
+ "prenorm": false,
50
+ "qkv_proj_bias": false,
51
+ "reorder_and_upcast_attn": false,
52
+ "resid_pdrop": 0.0,
53
  "rope_parameters": {
54
  "rope_theta": 1000.0,
55
  "rope_type": "default"
56
  },
57
+ "rotary_emb_base": 1000,
58
+ "rotary_emb_fraction": 1.0,
59
+ "rotary_emb_interleaved": false,
60
+ "rotary_emb_scale_base": null,
61
+ "rotary_scaling_factor": null,
62
+ "scale_attn_by_inverse_layer_idx": false,
63
+ "scale_attn_weights": true,
64
+ "summary_activation": null,
65
+ "summary_first_dropout": 0.0,
66
+ "summary_proj_to_labels": true,
67
+ "summary_type": "cls_index",
68
+ "summary_use_proj": true,
69
+ "torch_dtype": "float32",
70
  "transformers_version": "5.3.0.dev0",
71
  "type_vocab_size": 2,
72
+ "use_cache": true,
73
+ "use_flash_attn": true,
74
+ "use_rms_norm": false,
75
+ "use_xentropy": true,
76
  "vocab_size": 30528
77
  }
sentence_bert_config.json CHANGED
@@ -1,7 +1,4 @@
1
  {
2
  "max_seq_length": 8192,
3
- "do_lower_case": false,
4
- "model_args": {
5
- "safe_serialization": true
6
- }
7
  }
 
1
  {
2
  "max_seq_length": 8192,
3
+ "do_lower_case": false
 
 
 
4
  }