Nicolay Rusnachenko

nicolay-r

AI & ML interests

Information Retrieval・Medical Multimodal NLP (🖼+📝) Research Fellow @BU_Research・software developer http://arekit.io・PhD in NLP

Recent Activity

posted an update about 20 hours ago

📢 For those who in textual IR and experimenting with quick deployment of CoT / reasoning, the following update might be relevant. I am happy to announce new version of the bulk-chain 0.25.3. It is a no-string framework for quick application of reasoning schema adaptation over your data. https://github.com/nicolay-r/bulk-chain/releases/tag/0.25.3 The latest release brings huge updates on: ✅ Reforged mechanism of models inference that work in steraming mode. - Callbacks support for streaming mode (earlier only in demo) - Deployment of various clients (shell, tksheet; see attachment) ✅ Support for batching (earlier in API mode only) ✅ Optional caching of inferred data in SQlite (always enabled earlier) - This now makes possible to faster launch small (but mighty) LLMs 🌟 Project: https://github.com/nicolay-r/bulk-chain 🌌 Proviers: https://github.com/nicolay-r/nlp-thirdgate

liked a model 15 days ago

NX-AI/xLSTM-7b

posted an update 15 days ago

The Concept behind xLSTM has recently turn into the xLSTM-7B model that showcase the performance in the category of the similar-scale Gemma 7B, LLama2 7B, FlaconMamba 7B but with higher performing Inference Kernel Model: https://huggingface.co/NX-AI/xLSTM-7b Paper: https://arxiv.org/abs/2503.13427

View all activity

Organizations

None yet

Posts 66

Post

423

📢 For those who in textual IR and experimenting with quick deployment of CoT / reasoning, the following update might be relevant. I am happy to announce new version of the bulk-chain 0.25.3. It is a no-string framework for quick application of reasoning schema adaptation over your data.

https://github.com/nicolay-r/bulk-chain/releases/tag/0.25.3

The latest release brings huge updates on:
✅ Reforged mechanism of models inference that work in steraming mode.
- Callbacks support for streaming mode (earlier only in demo)
- Deployment of various clients (shell, tksheet; see attachment)
✅ Support for batching (earlier in API mode only)
✅ Optional caching of inferred data in SQlite (always enabled earlier)
- This now makes possible to faster launch small (but mighty) LLMs

🌟 Project: https://github.com/nicolay-r/bulk-chain
🌌 Proviers: https://github.com/nicolay-r/nlp-thirdgate

Post

1639

The Concept behind xLSTM has recently turn into the xLSTM-7B model that showcase the performance in the category of the similar-scale Gemma 7B, LLama2 7B, FlaconMamba 7B but with higher performing Inference Kernel

Model: NX-AI/xLSTM-7b
Paper: https://arxiv.org/abs/2503.13427

View all Posts