mkurman/Qwen2.5-14B-DeepSeek-R1-1M
Text Generation
ā¢
Updated
ā¢
10.2k
ā¢
50
Tuan Tran
tuantm
Ā·
AI & ML interests
None yet
Recent Activity
liked
a model
25 days ago
mkurman/Qwen2.5-14B-DeepSeek-R1-1M
liked
a model
25 days ago
FuseAI/FuseO1-DeepSeekR1-QwQ-SkyT1-32B-Preview
liked
a model
about 1 month ago
google/timesfm-2.0-500m-pytorch
Organizations
tuantm's activity
liked
2
models
25 days ago
liked
a
model
about 1 month ago
liked
a
model
about 2 months ago
liked
a
model
2 months ago
liked
a
model
3 months ago
liked
a
dataset
3 months ago
liked
5
models
4 months ago
tablegpt/TableGPT2-7B
Updated
ā¢
1.99k
ā¢
166
facebook/MobileLLM-1B
Text Generation
ā¢
Updated
ā¢
3.95k
ā¢
116
facebook/MobileLLM-125M
Text Generation
ā¢
Updated
ā¢
5.64k
ā¢
100
HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1
Sentence Similarity
ā¢
Updated
ā¢
32.8k
ā¢
32
Marqo/marqo-ecommerce-embeddings-L
Updated
ā¢
81.4k
ā¢
31
reacted to
tomaarsen's
post with š„
4 months ago
Post
7073
š£ Sentence Transformers v3.2.0 is out, marking the biggest release for inference in 2 years! 2 new backends for embedding models: ONNX (+ optimization & quantization) and OpenVINO, allowing for speedups up to 2x-3x AND Static Embeddings for 500x speedups at 10-20% accuracy cost.
1ļøā£ ONNX Backend: This backend uses the ONNX Runtime to accelerate model inference on both CPU and GPU, reaching up to 1.4x-3x speedup depending on the precision. We also introduce 2 helper methods for optimizing and quantizing models for (much) faster inference.
2ļøā£ OpenVINO Backend: This backend uses Intel their OpenVINO instead, outperforming ONNX in some situations on CPU.
Usage is as simple as
š Another major new feature is Static Embeddings: think word embeddings like GLoVe and word2vec, but modernized. Static Embeddings are bags of token embeddings that are summed together to create text embeddings, allowing for lightning-fast embeddings that don't require any neural networks. They're initialized in one of 2 ways:
1ļøā£ via Model2Vec, a new technique for distilling any Sentence Transformer models into static embeddings. Either via a pre-distilled model with
2ļøā£ Random initialization. This requires finetuning, but finetuning is extremely quick (e.g. I trained with 3 million pairs in 7 minutes). My final model was 6.6% worse than bge-base-en-v1.5, but 500x faster on CPU.
Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.2.0
Documentation on Speeding up Inference: https://sbert.net/docs/sentence_transformer/usage/efficiency.html
1ļøā£ ONNX Backend: This backend uses the ONNX Runtime to accelerate model inference on both CPU and GPU, reaching up to 1.4x-3x speedup depending on the precision. We also introduce 2 helper methods for optimizing and quantizing models for (much) faster inference.
2ļøā£ OpenVINO Backend: This backend uses Intel their OpenVINO instead, outperforming ONNX in some situations on CPU.
Usage is as simple as
SentenceTransformer("all-MiniLM-L6-v2", backend="onnx"). Does your model not have an ONNX or OpenVINO file yet? No worries - it'll be autoexported for you. Thank me later šš Another major new feature is Static Embeddings: think word embeddings like GLoVe and word2vec, but modernized. Static Embeddings are bags of token embeddings that are summed together to create text embeddings, allowing for lightning-fast embeddings that don't require any neural networks. They're initialized in one of 2 ways:
1ļøā£ via Model2Vec, a new technique for distilling any Sentence Transformer models into static embeddings. Either via a pre-distilled model with
from_model2vec or with from_distillation where you do the distillation yourself. It'll only take 5 seconds on GPU & 2 minutes on CPU, no dataset needed.2ļøā£ Random initialization. This requires finetuning, but finetuning is extremely quick (e.g. I trained with 3 million pairs in 7 minutes). My final model was 6.6% worse than bge-base-en-v1.5, but 500x faster on CPU.
Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.2.0
Documentation on Speeding up Inference: https://sbert.net/docs/sentence_transformer/usage/efficiency.html
- 1 reply
liked
a
model
4 months ago
liked
a
model
5 months ago
liked
a
dataset
5 months ago
upvoted
a
paper
5 months ago
liked
3
datasets
5 months ago