s-batman/Ornith-1.0-35B-NVFP4-MTP-GGUF

Update README.md

Update all references: ornith-1.0-35b-NVFP4_MOE-MTP.gguf -> ornith-1.0-35b-MXFP4_MOE-MTP.gguf (matching the rename on HF). The MXFP4+MTP file is now correctly named.

Rename: ornith-1.0-35b-NVFP4_MOE-MTP.gguf -> ornith-1.0-35b-MXFP4_MOE-MTP.gguf. The old file used llama-quantize ftype MXFP4_MOE (tensor type 39); old filename was misleading.

Copy files from models/s-batman/Ornith-1.0-35B-NVFP4-MTP-GGUF

Add true NVFP4 file (tensor type 40, 21.31 GB); existing MXFP4 file retained

Removing broken NVFP4 file (2D linears were wrongly NVFP4-quantized); will re-upload with fixed routing

Add true NVFP4 file (tensor type 40, 21.0 GB); existing MXFP4 file retained

Upload ornith-1.0-35b-NVFP4_MOE-MTP.gguf with huggingface_hub

Upload video_preprocessor_config.json with huggingface_hub

Upload model.safetensors.index.json with huggingface_hub

Upload generation_config.json with huggingface_hub

Upload processor_config.json with huggingface_hub

Upload preprocessor_config.json with huggingface_hub

Upload vocab.json with huggingface_hub

Upload tokenizer_config.json with huggingface_hub

Upload tokenizer.json with huggingface_hub

Upload config.json with huggingface_hub

Upload chat_template.jinja with huggingface_hub

Upload .gitattributes with huggingface_hub

Upload LICENSE with huggingface_hub

Upload README.md with huggingface_hub

initial commit