JT

jtvino

AI & ML interests

None yet

Recent Activity

reacted to tomaarsen's post with 🔥 15 days ago

🐦‍🔥 I've just published Sentence Transformers v5.2.0! It introduces multi-processing for CrossEncoder (rerankers), multilingual NanoBEIR evaluators, similarity score outputs in mine_hard_negatives, Transformers v5 support and more. Details: - CrossEncoder multi-processing: Similar to SentenceTransformer and SparseEncoder, you can now use multi-processing with CrossEncoder rerankers. Useful for multi-GPU and CPU settings, and simple to configure: just `device=["cuda:0", "cuda:1"]` or `device=["cpu"]*4` on the `model.predict` or `model.rank` calls. - Multilingual NanoBEIR Support: You can now use community translations of the tiny NanoBEIR retrieval benchmark instead of only the English one, by passing `dataset_id`, e.g. `dataset_id="lightonai/NanoBEIR-de"` for the German benchmark. - Similarity scores in Hard Negatives Mining: When mining for hard negatives to create a strong training dataset, you can now pass `output_scores=True` to get similarity scores returned. This can be useful for some distillation losses! - Transformers v5: This release works with both Transformers v4 and the upcoming v5. In the future, Sentence Transformers will only work with Transformers v5, but not yet! - Python 3.9 deprecation: Now that Python 3.9 has lost security support, Sentence Transformers no longer supports it. Check out the full changelog for more details: https://github.com/huggingface/sentence-transformers/releases/tag/v5.2.0 I'm quite excited about what's coming. There's a huge draft PR with a notable refactor in the works that should bring some exciting support. Specifically, better multimodality, rerankers, and perhaps some late interaction in the future!

new activity 24 days ago

mistralai/Mistral-Large-3-675B-Instruct-2512-NVFP4:VLLM Nightly Docker Image failing to load

liked a model about 2 months ago

maya-research/maya1

View all activity

Organizations

upvoted a paper 2 months ago

UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action

Paper • 2510.17790 • Published Oct 20 • 5

upvoted a paper 8 months ago

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Paper • 2505.03335 • Published May 6 • 188

upvoted a collection 8 months ago

NextCoder

Collection

NextCoder family of code-editing LMs developed with Selective Knowledge Transfer and its training data. • 6 items • Updated Jul 9 • 74

upvoted an article 8 months ago

Article

Uncensor any LLM with abliteration

Jun 13, 2024

•

744

upvoted an article 9 months ago

Article

Custom Vibe Coding Quest Part 2: 🚙 Fine-Tuning Gemma 3 for Code Reasoning

Apr 1

•

upvoted 2 papers about 2 years ago

LLM in a flash: Efficient Large Language Model Inference with Limited Memory

Paper • 2312.11514 • Published Dec 12, 2023 • 260

3D-LFM: Lifting Foundation Model

Paper • 2312.11894 • Published Dec 19, 2023 • 15

JT

AI & ML interests

Recent Activity

Organizations

jtvino's activity

Uncensor any LLM with abliteration

Custom Vibe Coding Quest Part 2: 🚙 Fine-Tuning Gemma 3 for Code Reasoning