Statuo/ArliAI-MS-24b-RPMAX-EXL2-4bpw
Updated
•
8
•
1
DeathGodlike
DeathGodlike
AI & ML interests
None yet
Recent Activity
liked
a model
4 days ago
Statuo/ArliAI-MS-24b-RPMAX-EXL2-4bpw
liked
a model
4 days ago
ArliAI/Mistral-Small-24B-ArliAI-RPMax-v1.4
liked
a model
4 days ago
zerofata/L3.3-GeneticLemonade-Unleashed-70B
Organizations
None yet
liked
4
models
4 days ago
liked
a
model
5 days ago
reacted to
tomaarsen's
post with 🔥
5 days ago
Post
2187
‼️Sentence Transformers v5.0 is out! The biggest update yet introduces Sparse Embedding models, encode methods improvements, Router module for asymmetric models & much more. Sparse + Dense = 🔥 hybrid search performance! Details:
1️⃣ Sparse Encoder Models
Brand new support for sparse embedding models that generate high-dimensional embeddings (30,000+ dims) where <1% are non-zero:
- Full SPLADE, Inference-free SPLADE, and CSR architecture support
- 4 new modules, 12 new losses, 9 new evaluators
- Integration with @elastic-co , @opensearch-project , @NAVER LABS Europe, @qdrant , @IBM , etc.
- Decode interpretable embeddings to understand token importance
- Hybrid search integration to get the best of both worlds
2️⃣ Enhanced Encode Methods & Multi-Processing
- Introduce encode_query & encode_document automatically use predefined prompts
- No more manual pool management - just pass device list directly to encode()
- Much cleaner and easier to use than the old multi-process approach
3️⃣ Router Module & Advanced Training
- Router module with different processing paths for queries vs documents
- Custom learning rates for different parameter groups
- Composite loss logging - see individual loss components
- Perfect for two-tower architectures
4️⃣ Comprehensive Documentation & Training
- New Training Overview, Loss Overview, API Reference docs
- 6 new training example documentation pages
- Full integration examples with major search engines
- Extensive blogpost on training sparse models
Read the comprehensive blogpost about training sparse embedding models: https://huggingface.co/blog/train-sparse-encoder
See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/v5.0.0
What's next? We would love to hear from the community! What sparse encoder models would you like to see? And what new capabilities should Sentence Transformers handle - multimodal embeddings, late interaction models, or something else? Your feedback shapes our roadmap!
1️⃣ Sparse Encoder Models
Brand new support for sparse embedding models that generate high-dimensional embeddings (30,000+ dims) where <1% are non-zero:
- Full SPLADE, Inference-free SPLADE, and CSR architecture support
- 4 new modules, 12 new losses, 9 new evaluators
- Integration with @elastic-co , @opensearch-project , @NAVER LABS Europe, @qdrant , @IBM , etc.
- Decode interpretable embeddings to understand token importance
- Hybrid search integration to get the best of both worlds
2️⃣ Enhanced Encode Methods & Multi-Processing
- Introduce encode_query & encode_document automatically use predefined prompts
- No more manual pool management - just pass device list directly to encode()
- Much cleaner and easier to use than the old multi-process approach
3️⃣ Router Module & Advanced Training
- Router module with different processing paths for queries vs documents
- Custom learning rates for different parameter groups
- Composite loss logging - see individual loss components
- Perfect for two-tower architectures
4️⃣ Comprehensive Documentation & Training
- New Training Overview, Loss Overview, API Reference docs
- 6 new training example documentation pages
- Full integration examples with major search engines
- Extensive blogpost on training sparse models
Read the comprehensive blogpost about training sparse embedding models: https://huggingface.co/blog/train-sparse-encoder
See the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/v5.0.0
What's next? We would love to hear from the community! What sparse encoder models would you like to see? And what new capabilities should Sentence Transformers handle - multimodal embeddings, late interaction models, or something else? Your feedback shapes our roadmap!
liked
a
model
6 days ago
upvoted
a
collection
6 days ago
liked
a
model
6 days ago
upvoted
2
collections
6 days ago
liked
7
models
7 days ago
unsloth/FLUX.1-Kontext-dev-GGUF
Image-to-Image
•
12B
•
Updated
•
10.5k
•
28
Delta-Vector/Austral-24B-Winton
Text Generation
•
24B
•
Updated
•
321
•
•
11
zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B
Text Generation
•
71B
•
Updated
•
2.13k
•
•
15
Steelskull/L3.3-Shakudo-70b
71B
•
Updated
•
237
•
14
Delta-Vector/Shimamura-70B
71B
•
Updated
•
13
•
1
Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2
Text Generation
•
31B
•
Updated
•
425
•
13
SlerpE/CardProjector-24B-v3
24B
•
Updated
•
261
•
13
reacted to
merve's
post with 🔥
7 days ago
Post
2420
tis the year of any-to-any/omni models 🤠
ByteDance-Seed/BAGEL-7B-MoT 7B native multimodal model that understands and generates both image + text
it outperforms leading VLMs like Qwen 2.5-VL 👏 and has Apache 2.0 license 😱
ByteDance-Seed/BAGEL-7B-MoT 7B native multimodal model that understands and generates both image + text
it outperforms leading VLMs like Qwen 2.5-VL 👏 and has Apache 2.0 license 😱
upvoted
a
collection
7 days ago