6 6 20

Inha Hwang

HyperBlaze

LightningHyperBlaze45654

AI & ML interests

Am I an AI? Maybe or maybe not :) I’ll try my best as a language model to assist users questions

Recent Activity

liked a model about 1 month ago

amphion/MaskGCT

View all activity

Organizations

HyperBlaze's activity

liked a model about 1 month ago

amphion/MaskGCT

Text-to-Speech • Updated 3 days ago • 4 • 257

upvoted a paper 3 months ago

Enhancing Structured-Data Retrieval with GraphRAG: Soccer Data Case Study

Paper • 2409.17580 • Published Sep 26 • 7

liked a model 3 months ago

meta-llama/Llama-3.2-11B-Vision-Instruct

Image-Text-to-Text • Updated 21 days ago • 2.8M • • 1.15k

upvoted a collection 3 months ago

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated 27 days ago • 444

upvoted an article 3 months ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Sep 18

• 213

liked a Space 3 months ago

Running

139

🌖

Llama3.1 Instruct O1

liked a model 3 months ago

mistralai/Mistral-Small-Instruct-2409

Updated Oct 16 • 2.89M • 361

upvoted an article 3 months ago

Article

Accelerate 1.0.0

Sep 13

• 51

New activity in mattshumer/Reflection-Llama-3.1-70B 3 months ago

update model card to reflect the non-reproducibility of benchmark

#154 opened 3 months ago by

clem

It looks the model is in 8K context length. May I ask why context length of Llama3.1 is 128K

#153 opened 3 months ago by

tonyaw

reacted to tomaarsen's post with 🔥 3 months ago

Post

3743

🚀 Sentence Transformers v3.1 is out! Featuring a hard negatives mining utility to get better models out of your data, a new strong loss function, training with streaming datasets, custom modules, bug fixes, small additions and docs changes. Here's the details:

⛏ Hard Negatives Mining Utility: Hard negatives are texts that are rather similar to some anchor text (e.g. a question), but are not the correct match. They're difficult for a model to distinguish from the correct answer, often resulting in a stronger model after training.
📉 New loss function: This loss function works very well for symmetric tasks (e.g. clustering, classification, finding similar texts/paraphrases) and a bit less so for asymmetric tasks (e.g. question-answer retrieval).
💾 Streaming datasets: You can now train with the datasets.IterableDataset, which doesn't require downloading the full dataset to disk before training. As simple as "streaming=True" in your "datasets.load_dataset".
🧩 Custom Modules: Model authors can now customize a lot more of the components that make up Sentence Transformer models, allowing for a lot more flexibility (e.g. multi-modal, model-specific quirks, etc.)
✨ New arguments to several methods: encode_multi_process gets a progress bar, push_to_hub can now be done to different branches, and CrossEncoders can be downloaded to specific cache directories.
🐛 Bug fixes: Too many to name here, check out the release notes!
📝 Documentation: A particular focus on clarifying the batch samplers in the Package Reference this release.

Check out the full release notes here ⭐: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.1.0

I'm very excited to hear your feedback, and I'm looking forward to the future changes that I have planned, such as ONNX inference! I'm also open to suggestions for new features: feel free to send me your ideas.