Hugging Face's logo

NoesisLab
/
Collins-Embedding-3M

Sentence Similarity
sentence-transformers
Safetensors
English
feature-extraction
Model card Files
xet
 Community
OzTianlu commited on
Commit
ac22237
·
verified ·
1 Parent(s): 7ef4942

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -81,7 +81,7 @@ With V = 30522 and B = 512, Collins uses ~60× fewer parameters for the token en
81
  |---|---|---|---|---|
82
  | GloVe (6B, 300d) | Static Embedding | ~120M | ~0.50 | 0.0042 |
83
  | BERT-base (Mean Pool) | Contextual (no NLI FT) | 110M | ~0.50 | 0.0045 |
84
- | **Collins-Hash (Ours)** | **Hash + RoPE** | **3M** | **0.7114** | **0.237** |
85
  | paraphrase-MiniLM-L3-v2 | Contextual | 15M | ~0.75 | 0.050 |
86
  | BGE-micro-v2 | Contextual | 17M | ~0.76 | 0.044 |
87
  | paraphrase-MiniLM-L6-v2 | Contextual | 22M | ~0.79 | 0.036 |
 
81
  |---|---|---|---|---|
82
  | GloVe (6B, 300d) | Static Embedding | ~120M | ~0.50 | 0.0042 |
83
  | BERT-base (Mean Pool) | Contextual (no NLI FT) | 110M | ~0.50 | 0.0045 |
84
+ | **Collins (Ours)** | **Hash + RoPE** | **3M** | **0.7114** | **0.237** |
85
  | paraphrase-MiniLM-L3-v2 | Contextual | 15M | ~0.75 | 0.050 |
86
  | BGE-micro-v2 | Contextual | 17M | ~0.76 | 0.044 |
87
  | paraphrase-MiniLM-L6-v2 | Contextual | 22M | ~0.79 | 0.036 |