Hugging Face's logo

Snowflake
/
snowflake-arctic-embed-m-long

Sentence Similarity
sentence-transformers
ONNX
Safetensors
Transformers.js
nomic_bert
feature-extraction
mteb
arctic
snowflake-arctic-embed
custom_code
Eval Results
Inference Endpoints
Model card Files Community
12
spacemanidol commited on
Commit
0a63259
•
1 Parent(s): e580be1

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +57 -0
  2. model.safetensors +3 -0
  3. special_tokens_map.json +37 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +63 -0
  6. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/.model_and_tokenizer_cache/f5da535d605874f0c1155faed21ab4a9cb933b1a1c642a7afeccd2cbf9debcf3",
3
+ "activation_function": "swiglu",
4
+ "architectures": [
5
+ "NomicBertModel"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "configuration_hf_nomic_bert.NomicBertConfig",
10
+ "AutoModel": "modeling_hf_nomic_bert.NomicBertModel"
11
+ },
12
+ "bos_token_id": null,
13
+ "causal": false,
14
+ "dense_seq_output": true,
15
+ "embd_pdrop": 0.1,
16
+ "eos_token_id": null,
17
+ "fused_bias_fc": true,
18
+ "fused_dropout_add_ln": true,
19
+ "initializer_range": 0.02,
20
+ "layer_norm_epsilon": 1e-12,
21
+ "max_trained_positions": 2048,
22
+ "mlp_fc1_bias": false,
23
+ "mlp_fc2_bias": false,
24
+ "model_type": "nomic_bert",
25
+ "n_embd": 768,
26
+ "n_head": 12,
27
+ "n_inner": 3072,
28
+ "n_layer": 12,
29
+ "n_positions": 8192,
30
+ "pad_vocab_size_multiple": 64,
31
+ "parallel_block": false,
32
+ "parallel_block_tied_norm": false,
33
+ "prenorm": false,
34
+ "qkv_proj_bias": false,
35
+ "reorder_and_upcast_attn": false,
36
+ "resid_pdrop": 0.1,
37
+ "rotary_emb_base": 1000,
38
+ "rotary_emb_fraction": 1.0,
39
+ "rotary_emb_interleaved": false,
40
+ "rotary_emb_scale_base": null,
41
+ "rotary_scaling_factor": 2,
42
+ "scale_attn_by_inverse_layer_idx": false,
43
+ "scale_attn_weights": true,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.36.1",
51
+ "type_vocab_size": 2,
52
+ "use_cache": true,
53
+ "use_flash_attn": true,
54
+ "use_rms_norm": false,
55
+ "use_xentropy": true,
56
+ "vocab_size": 30528
57
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f469f6e6946f80f12edfe41d06b844098928ab6fb33b09c59028bc7405f068f8
3
+ size 546938168
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
50
+ "model_max_length": 8192,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "[PAD]",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "[SEP]",
56
+ "stride": 0,
57
+ "strip_accents": null,
58
+ "tokenize_chinese_chars": true,
59
+ "tokenizer_class": "BertTokenizer",
60
+ "truncation_side": "right",
61
+ "truncation_strategy": "longest_first",
62
+ "unk_token": "[UNK]"
63
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff