kshitijthakkar/qwen3.5-moe-0.87B-d0.8B

set tie_word_embeddings=False for GGUF/ollama compatibility

set tie_word_embeddings=True (both tensors identical, matching source models)

set tie_word_embeddings=False (both tensors present in checkpoint)

re-upload weights as sharded safetensors for model size detection

remove single-file safetensors (will re-upload as sharded)

remove non-standard index for single-file safetensors

add safetensors index for model size detection

fix README: add pipeline_tag and image-text-to-text tag

fix config.json: use nested text_config for HF model size detection

Add Qwen3.5 MoE 0.85B (dense-to-MoE from Qwen/Qwen3.5-0.8B)

Add Qwen3.5 MoE 0.85B (dense-to-MoE from Qwen/Qwen3.5-0.8B)

initial commit