Commit History

Fix model card: remove enforce-eager (fixed in vLLM 0.18.0 PR #35256)
e11369e
verified

raydelossantos commited on

Update model card: VLM architecture, enable-prefix-caching, weight structure docs
443770f
verified

raydelossantos commited on

Remove old 4-shard files (replaced by single model.safetensors)
9085a7c
verified

raydelossantos commited on

Fix weight keys for VLM: rename model.* to model.language_model.*, add visual encoder from base model
dfff36d
verified

raydelossantos commited on

Fix config.json: use VLM structure (model_type=qwen3_5, Qwen3_5ForConditionalGeneration) with quantization_config
cd328b1
verified

raydelossantos commited on

Add vision_config to config.json for vLLM VLM backbone compat
9fcb455
verified

raydelossantos commited on

Add processor_config.json with video processor for vLLM compat
9b0fbd6
verified

raydelossantos commited on

Add preprocessor_config.json for vLLM compatibility (text-only quant)
6e04c7a
verified

raydelossantos commited on

Upload config.json with huggingface_hub
c554222
verified

raydelossantos commited on

Upload folder using huggingface_hub
7520601
verified

raydelossantos commited on

Upload folder using huggingface_hub
d56b799
verified

raydelossantos commited on