Dongfu Jiang's picture

Dongfu Jiang

DongfuJiang

·

https://jdf-prog.github.io/

AI & ML interests

Large Language Model, Modality Reasoning and their evaluation

Recent Activity

upvoted a paper about 3 hours ago

Reinforcement Learning for Reasoning in Large Language Models with One Training Example

updated a model about 9 hours ago

VerlTool/torl-fsdp_agent-qwen_qwen2.5-7b-grpo-n16-b128-t1.0-lr1e-6new-190-step

updated a model about 9 hours ago

VerlTool/torl-fsdp_agent-qwen_qwen2.5-math-7b-grpo-n16-b128-t1.0-lr1e-6new-220-step

View all activity

Organizations

DongfuJiang's activity

New activity in llm-blender/pair-ranker 28 days ago

Adding `safetensors` variant of this model

#1 opened 3 months ago by

Update model metadata to set pipeline tag to the new `text-ranking`

#2 opened 28 days ago by

New activity in TIGER-Lab/Mantis-Instruct 4 months ago

Dreamsim: "Here are there images"

#4 opened 6 months ago by

New activity in TIGER-Lab/Mantis-Instruct 7 months ago

fix typo

#3 opened 7 months ago by

New activity in mistral-community/pixtral-12b-240910 7 months ago

Any Inference code?

#6 opened 8 months ago by

New activity in TIGER-Lab/Mantis-8B-Idefics2 8 months ago

No Chat Template

#1 opened 10 months ago by

New activity in TIGER-Lab/Mantis-Instruct 9 months ago

No images in dvqa subset

#2 opened 9 months ago by

New activity in zero-gpu-explorers/README 10 months ago

Error initializing ZeroGPU: Unknown

#80 opened 10 months ago by

commented 2 papers 10 months ago

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

Paper • 2406.11833 • Published Jun 17, 2024 • 64 •

Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning

Paper • 2406.12742 • Published Jun 18, 2024 • 15 •

commented a paper 11 months ago

MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs

Paper • 2406.11833 • Published Jun 17, 2024 • 64 •

New activity in TIGER-Lab/Mantis-8B-siglip-llama3 12 months ago

GGUF Quants?

#1 opened 12 months ago by

commented a paper 12 months ago

MANTIS: Interleaved Multi-Image Instruction Tuning

Paper • 2405.01483 • Published May 2, 2024 • 6 •

New activity in Mantis-VL/llava_next_mistral_7b_4096 about 1 year ago

How to fine tune this model?

#1 opened about 1 year ago by

New activity in TIGER-Lab/Mantis-llava-7b about 1 year ago

Newer llava versions 1.6 with multi image training!

#1 opened about 1 year ago by

New activity in Mantis-VL/MIQA_sample about 1 year ago

How about considering Q-Bench-Pair?

#2 opened about 1 year ago by

New activity in TIGER-Lab/TIGERScore-13B about 1 year ago

Adding Evaluation Results

#4 opened about 1 year ago by

leaderboard-pr-bot

New activity in llm-blender/PairRM over 1 year ago

I wonder if there is any possibility that you can make your collected pairwise dataset open-source ?

#4 opened over 1 year ago by

Run model with transformers?

#2 opened over 1 year ago by

What's the difference between llm-blender/PairRM and llm-blender/pair-ranker?

#3 opened over 1 year ago by