zai-org/GLM-5
Text Generation • 754B • Updated
• 183k • • 1.57k
Isak Westerlund
Westis
AI & ML interests
TTS, ASR, NLP
Recent Activity
liked
a model 14 days ago
zai-org/GLM-5 liked
a model 23 days ago
Qwen/Qwen3-Coder-Next liked
a model 27 days ago
MachineDelusions/LTX-2_Image2Video_Adapter_LoRa Organizations
liked a model 14 days ago
liked a model 23 days ago
liked a model 27 days ago
liked a model 29 days ago
liked 4 models about 1 month ago
liked 3 models 2 months ago
reacted to tomaarsen's post with 🔥 3 months ago
Post
3854
🐦🔥 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
- Multilingual NanoBEIR Support: You can now use community translations of the tiny NanoBEIR retrieval benchmark instead of only the English one, by passing
- Similarity scores in Hard Negatives Mining: When mining for hard negatives to create a strong training dataset, you can now pass
- 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!
- 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!
liked 4 models 3 months ago
liked a dataset 3 months ago
reacted to Juanxi's post with 🔥 3 months ago
Post
2022
ScalingOpt | Welcome to join and co-build the Optimization Community!
ScalingOpt is a professional platform focusing on optimization for large-scale deep learning, aiming to advocate for "Optimization at Scale," which means verifiable and scalable optimization algorithms.
This community platform is dedicated to gathering, discovering, comparing, and contributing various cutting-edge optimizers and optimization algorithms.
It's not just a simple Awesome List, it also includes:
Visualizations: Covers visualization scripts for the Rosenbrock Function and the Rastrigin Function for users to freely explore.
Benchmark: We recommend Algoperf as the primary source, along with other verifiable benchmarks and analysis articles, for users to reference the best optimizer.
Papers & Blogs Recommendation: The platform summarizes high-quality papers and blogs from recent years, and continuously adds the latest papers based on daily arXiv updates, currently totaling nearly a hundred articles.
Tutorials Sharing: The platform collects quality resources from the community and is independently producing a "From Classical to Modern Optimizers" Tutorial Series, which is expected to be updated by the end of the month.
We welcome everyone to use it and provide valuable feedback. We also welcome you to join us in co-building the community and focusing on the latest developments in optimization algorithms. The ScalingOpt community platform will be continuously updated.
We hope everyone can give ScalingOpt a star ⭐️. Thank you very much 🙏
Website: https://tianshijing.github.io/ScalingOpt
Github: https://github.com/tianshijing/ScalingOpt
ScalingOpt is a professional platform focusing on optimization for large-scale deep learning, aiming to advocate for "Optimization at Scale," which means verifiable and scalable optimization algorithms.
This community platform is dedicated to gathering, discovering, comparing, and contributing various cutting-edge optimizers and optimization algorithms.
It's not just a simple Awesome List, it also includes:
Visualizations: Covers visualization scripts for the Rosenbrock Function and the Rastrigin Function for users to freely explore.
Benchmark: We recommend Algoperf as the primary source, along with other verifiable benchmarks and analysis articles, for users to reference the best optimizer.
Papers & Blogs Recommendation: The platform summarizes high-quality papers and blogs from recent years, and continuously adds the latest papers based on daily arXiv updates, currently totaling nearly a hundred articles.
Tutorials Sharing: The platform collects quality resources from the community and is independently producing a "From Classical to Modern Optimizers" Tutorial Series, which is expected to be updated by the end of the month.
We welcome everyone to use it and provide valuable feedback. We also welcome you to join us in co-building the community and focusing on the latest developments in optimization algorithms. The ScalingOpt community platform will be continuously updated.
We hope everyone can give ScalingOpt a star ⭐️. Thank you very much 🙏
Website: https://tianshijing.github.io/ScalingOpt
Github: https://github.com/tianshijing/ScalingOpt
- 1 reply
liked a model 3 months ago
liked a model 4 months ago
