0.16.1

Recent updates

Version 0.16.1

• Add "start with" parameter to pre-fill assistant response & backend support (doesn't work with all models) - aka 'Sure,' support.

0.16.0

Recent updates

Version 0.16.0

• new model support: microsoft/Phi-3-vision-128k-instruct

0.15.1

Recent updates

Version 0.15.1

• new model support: OpenGVLab/Mini-InternVL-Chat-2B-V1-5

0.15.0

Recent updates

Version 0.15.0

• new model support: cogvlm2-llama3-chinese-chat-19B, cogvlm2-llama3-chat-19B

0.14.0

Recent updates

Version: 0.14.0

• docker-compose.yml: Assume the runtime supports the device (ie. nvidia)
• new model support: qihoo360/360VL-8B, qihoo360/360VL-70B (70B loading error, see note, also too large for me to test because 4bit & 8bit are also not working for me - hopefully a quantized model comes out soon)
• new model support: BAAI/Emu2-Chat, Can be slow to load, may need --max-memory option control the loading on multiple gpus
• new model support: TIGER-Labs/Mantis: Mantis-8B-siglip-llama3, Mantis-8B-clip-llama3, Mantis-8B-Fuyu

0.13.0

Recent updates

Version: 0.13.0

• new model support: InternLM-XComposer2-4KHD
• new model support: BAAI/Bunny-Llama-3-8B-V
• new model support: qresearch/llama-3-vision-alpha-hf

0.12.1

Recent updates

Version: 0.12.1

• Fix: data: urls, revert load_image change

0.12.0

Recent updates

Version: 0.12.0

• new model support: HuggingFaceM4/idefics2-8b, HuggingFaceM4/idefics2-8b-AWQ
• Fix: remove prompt from output of InternVL-Chat-V1-5

0.11.0

Recent updates

Version: 0.11.0

• new model support: OpenGVLab/InternVL-Chat-V1-5, up to 4k resolution, top opensource model
• MiniGemini renamed MGM upstream

0.10.0

Changes

• new model support: adept/fuyu-8b