Sentence Similarity
PEFT
Safetensors
English
text-embedding
embeddings
information-retrieval
beir
text-classification
language-model
text-clustering
text-semantic-similarity
text-evaluation
text-reranking
feature-extraction
Sentence Similarity
natural_questions
ms_marco
fever
hotpot_qa
mteb
Eval Results
Update README.md
Browse files
README.md
CHANGED
@@ -3,12 +3,10 @@ library_name: transformers
|
|
3 |
tags: []
|
4 |
---
|
5 |
|
6 |
-
# LLM2Vec
|
7 |
|
8 |
-
> 2
|
9 |
-
|
10 |
-
- **Repository:**
|
11 |
-
- **Paper:**
|
12 |
|
13 |
|
14 |
## Installation
|
@@ -60,5 +58,3 @@ cos_sim = torch.mm(q_reps_norm, d_reps_norm.transpose(0, 1))
|
|
60 |
print(cos_sim.tolist())
|
61 |
|
62 |
```
|
63 |
-
|
64 |
-
## Citation
|
|
|
3 |
tags: []
|
4 |
---
|
5 |
|
6 |
+
# LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
|
7 |
|
8 |
+
> LLM2Vec is a simple recipe to convert decoder-only LLMs into text encoders. It consists of 3 simple steps: 1) enabling bidirectional attention, 2) masked next token prediction, and 3) unsupervised contrastive learning. The model can be further fine-tuned to achieve state-of-the-art performance.
|
9 |
+
- **Repository:** https://github.com/McGill-NLP/llm2vec
|
|
|
|
|
10 |
|
11 |
|
12 |
## Installation
|
|
|
58 |
print(cos_sim.tolist())
|
59 |
|
60 |
```
|
|
|
|