Hugging Face's logo

rasyosef
/
snowflake-arctic-embed-l-v2.0-finetuned-amharic

Sentence Similarity
sentence-transformers
Safetensors
English
Amharic
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:40237
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Model card Files
xet
Community
rasyosef commited on
Commit
2d5b6c6
·
verified ·
1 Parent(s): ff7cf6e

Add new SentenceTransformer model

Browse files
Files changed (8) hide show
  1. README.md +0 -0
  2. config.json +4 -2
  3. config_sentence_transformers.json +2 -2
  4. model.safetensors +1 -1
  5. sentence_bert_config.json +1 -1
  6. sentencepiece.bpe.model +3 -0
  7. tokenizer.json +1 -1
  8. tokenizer_config.json +1 -1
README.md CHANGED
The diff for this file is too large to render. See raw diff
 
config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "Snowflake/snowflake-arctic-embed-l-v2.0",
3
  "architectures": [
4
  "XLMRobertaModel"
5
  ],
@@ -13,6 +12,9 @@
13
  "initializer_range": 0.02,
14
  "intermediate_size": 4096,
15
  "layer_norm_eps": 1e-05,
 
 
 
16
  "max_position_embeddings": 8194,
17
  "model_type": "xlm-roberta",
18
  "num_attention_heads": 16,
@@ -21,7 +23,7 @@
21
  "pad_token_id": 1,
22
  "position_embedding_type": "absolute",
23
  "torch_dtype": "float32",
24
- "transformers_version": "4.48.3",
25
  "type_vocab_size": 1,
26
  "use_cache": true,
27
  "vocab_size": 250002
 
1
  {
 
2
  "architectures": [
3
  "XLMRobertaModel"
4
  ],
 
12
  "initializer_range": 0.02,
13
  "intermediate_size": 4096,
14
  "layer_norm_eps": 1e-05,
15
+ "matryoshka_dimensions": [
16
+ 256
17
+ ],
18
  "max_position_embeddings": 8194,
19
  "model_type": "xlm-roberta",
20
  "num_attention_heads": 16,
 
23
  "pad_token_id": 1,
24
  "position_embedding_type": "absolute",
25
  "torch_dtype": "float32",
26
+ "transformers_version": "4.51.3",
27
  "type_vocab_size": 1,
28
  "use_cache": true,
29
  "vocab_size": 250002
config_sentence_transformers.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "__version__": {
3
- "sentence_transformers": "3.4.1",
4
- "transformers": "4.48.3",
5
  "pytorch": "2.6.0+cu124"
6
  },
7
  "prompts": {
 
1
  {
2
  "__version__": {
3
+ "sentence_transformers": "4.1.0",
4
+ "transformers": "4.51.3",
5
  "pytorch": "2.6.0+cu124"
6
  },
7
  "prompts": {
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cef2c8dffdea22ed6442db9c624b8c58f4e75c2bbba0ce4f9299088dacecf2d
3
  size 2271064456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df629612f5a2cbf9cdf44e91672dde8844eb823d8a9ff604d1a611678ba71d1
3
  size 2271064456
sentence_bert_config.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "max_seq_length": 8192,
3
  "do_lower_case": false
4
  }
 
1
  {
2
+ "max_seq_length": 1024,
3
  "do_lower_case": false
4
  }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
3
  size 17083053
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e3b8957de04e3a4ed42b1a11381556f9adad8d0d502b9dd071c75f626b28f40
3
  size 17083053
tokenizer_config.json CHANGED
@@ -48,7 +48,7 @@
48
  "extra_special_tokens": {},
49
  "mask_token": "<mask>",
50
  "max_length": 512,
51
- "model_max_length": 8192,
52
  "pad_to_multiple_of": null,
53
  "pad_token": "<pad>",
54
  "pad_token_type_id": 0,
 
48
  "extra_special_tokens": {},
49
  "mask_token": "<mask>",
50
  "max_length": 512,
51
+ "model_max_length": 1024,
52
  "pad_to_multiple_of": null,
53
  "pad_token": "<pad>",
54
  "pad_token_type_id": 0,