Nenad Banfic's picture

6

Nenad Banfic

nenad1002

·

nenad1002

AI & ML interests

NLP, LLM, Lora, Reft, DPO, RLHF

Recent Activity

updated a model 3 days ago

nenad1002/NVIDIA-Nemotron-3.5-ASR-Streaming-Multilingual-0.6b-onnx-int4

published a model 4 days ago

nenad1002/NVIDIA-Nemotron-3.5-ASR-Streaming-Multilingual-0.6b-onnx-int4

updated a model 6 days ago

nenad1002/NVIDIA-Nemotron-3.5-ASR-Streaming-Multilingual-0.6b-onnx-int4-autodetect

View all activity

Organizations

New activity in nvidia/parakeet-tdt-0.6b-v3 17 days ago

The model sometimes drops full sentences

#42 opened 17 days ago by

New activity in CohereLabs/cohere-transcribe-03-2026 19 days ago

Can Cohere somehow handle punctuation and capitalization on chunk boundaries?

#39 opened 19 days ago by

New activity in Qwen/Qwen3-ASR-1.7B 4 months ago

Any plan to open the streaming model to run without vLLM?

#6 opened 4 months ago by

New activity in nenad1002/gemma3-gaia-pt-br-4b-it 10 months ago

make this a CPU model

#2 opened 10 months ago by

Create inference_model.json

#1 opened 10 months ago by

New activity in onnxruntime/Gemma-3-ONNX 10 months ago

Adapt vision and embedding models to v4.53.2 Gemma3 modeling code

#1 opened 10 months ago by