Today
-
Quantize the LM head to NVFP4 (22 % faster decode, 2 GB smaller), add MTP and AWQ comparison to the card
-
Card: image input via the plugin, vision check
Yesterday
-
Add model-00002-of-00002.safetensors
-
Add model-00001-of-00002.safetensors
-
Add video_preprocessor_config.json
-
Add tokenizer.json
-
Add tokenizer_config.json
-
Add processor_config.json
-
Add preprocessor_config.json
-
Add model.safetensors.index.json
-
Add modeling_sensenova_loop.py
-
Add hf_quant_config.json
-
Add generation_config.json
-
Add chat_template.jinja
-
Add config.json
-
Add README.md
-
initial commit