11 14

Neural Magic Research

nm-research

AI & ML interests

None yet

Recent Activity

published a model about 19 hours ago

RedHatAI/Mixtral-8x22B-v0.1-quantized.w4a16

published a model about 19 hours ago

RedHatAI/phi-4-FP8-dynamic

published a model about 19 hours ago

RedHatAI/Llama-3.3-70B-Instruct-FP8-dynamic

View all activity

Organizations

nm-research's activity

New activity in RedHatAI/Qwen2.5-VL-7B-Instruct-quantized.w4a16 9 days ago

Breaking change in transformers

#1 opened 10 days ago by

maldv

New activity in RedHatAI/Qwen2.5-VL-7B-Instruct-FP8-Dynamic 9 days ago

Update preprocessor_config.json

#4 opened 18 days ago by

ManishThota

New activity in RedHatAI/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic about 2 months ago

Calibration dataset

#1 opened about 2 months ago by

bullerwins

Update tokenizer_config.json

#3 opened about 2 months ago by

erichartford

New activity in RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16 about 2 months ago

Update README.md

#1 opened about 2 months ago by

nm-research

New activity in RedHatAI/Mistral-Small-24B-Instruct-2501-FP8-Dynamic 2 months ago

Add OpenLLM Leaderboard V1 and V2 evals

#1 opened 2 months ago by

nm-research

New activity in RedHatAI/Qwen2-VL-72B-Instruct-quantized.w4a16 2 months ago

Update config.json

#1 opened 2 months ago by

nm-research

New activity in RedHatAI/pixtral-12b-FP8-dynamic 5 months ago

Update model card

#1 opened 5 months ago by

nm-research

New activity in nm-testing/llava-1.5-7b-hf-FP8-dynamic 5 months ago

Add chat_template to tokenizer_config.json

#1 opened 5 months ago by

nm-research

New activity in RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8 8 months ago

Update README.md

#1 opened 8 months ago by

nm-research

New activity in RedHatAI/Phi-3-mini-128k-instruct-FP8 8 months ago

fix: align tokenizer_config.json with upstream instruct prompt format

#2 opened 8 months ago by

justinthelaw