Hugging Face's logo

ibm-granite
/
granite-embedding-30m-english

Sentence Similarity
sentence-transformers
PyTorch
ONNX
Safetensors
Transformers
English
roberta
feature-extraction
language
granite
embeddings
mteb
text-embeddings-inference
Model card Files
xet
Community
6

granite-embedding-30m-r1.1

#7
by pawasthy - opened
base: refs/heads/granite-embedding-30m-r1.1
←
from: refs/pr/7
Discussion Files changed
+250472
-20
Files changed (7) hide show
  1. README.md +1 -13
  2. config.json +1 -1
  3. merges.txt +1 -1
  4. pytorch_model.bin +2 -2
  5. special_tokens_map.json +51 -1
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +59 -1
README.md CHANGED
@@ -1,16 +1,4 @@
1
- ---
2
- language:
3
- - en
4
- license: apache-2.0
5
- library_name: sentence-transformers
6
- tags:
7
- - language
8
- - granite
9
- - embeddings
10
- - mteb
11
- - transformers
12
- pipeline_tag: sentence-similarity
13
- ---
14
  # Granite-Embedding-30m-English (revision r1.1)
15
 
16
  **News:**
 
1
+
 
 
 
 
 
 
 
 
 
 
 
 
2
  # Granite-Embedding-30m-English (revision r1.1)
3
 
4
  **News:**
config.json CHANGED
@@ -20,7 +20,7 @@
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "torch_dtype": "bfloat16",
23
- "transformers_version": "4.15.0",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 50265
 
20
  "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.48.0",
24
  "type_vocab_size": 2,
25
  "use_cache": true,
26
  "vocab_size": 50265
merges.txt CHANGED
@@ -1,4 +1,4 @@
1
- #version: 0.2 - Trained by `huggingface/tokenizers`
2
  Ġ t
3
  Ġ a
4
  h e
 
1
+ #version: 0.2
2
  Ġ t
3
  Ġ a
4
  h e
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c8fffb9eed339923271999acc56019c9382db20234fa4a0e9c41c417c2c17b
3
- size 60630897
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aafc4c906ec32a70a6a47aa6ff446b3b9b27a737c54fa07cbed13ce853298b8
3
+ size 60605052
special_tokens_map.json CHANGED
@@ -1 +1,51 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1,59 @@
1
- {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "added_tokens_decoder": {"0": {"content": "<s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "1": {"content": "<pad>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "2": {"content": "</s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "3": {"content": "<unk>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false, "special": true}, "50264": {"content": "<mask>", "lstrip": true, "normalized": true, "rstrip": false, "single_word": false, "special": true}}, "additional_special_tokens": [], "clean_up_tokenization_spaces": true, "model_max_length": 512, "special_tokens_map_file": "special_tokens_map.json", "name_or_path": "granite-embedding-30m-english", "tokenizer_class": "RobertaTokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "additional_special_tokens": [],
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": true,
48
+ "cls_token": "<s>",
49
+ "eos_token": "</s>",
50
+ "errors": "replace",
51
+ "extra_special_tokens": {},
52
+ "mask_token": "<mask>",
53
+ "model_max_length": 512,
54
+ "pad_token": "<pad>",
55
+ "sep_token": "</s>",
56
+ "tokenizer_class": "RobertaTokenizer",
57
+ "trim_offsets": true,
58
+ "unk_token": "<unk>"
59
+ }