HuanjinYao/Mulberry_llava_8b

Model

stars

commits

linked in READMEs

Feb 5, 2025

updated

conversational

endpoints_compatible

image-text-to-text

llava_next

safetensors

text-generation-inference

transformers

README

Mulberry

Mulberry-llava-8b is a step-by-step reasoning model trained on the Mulberry-260K SFT dataset, which was generated through collective knowledge search using CoMCTS.

For reasoning inference, please refer to our GitHub.

Paper: https://arxiv.org/abs/2412.18319

Code: https://github.com/HJYao00/Mulberry

More Details

Base Model: https://huggingface.co/llava-hf/llama3-llava-next-8b-hf

Training Framework: LLaMA-Factory

Hardware: 8x NVIDIA H100

Contributors

HuanjinYao

10 commits

nielsr

1 commits

Similar repos

HuanjinYao/Mulberry_llama_11b

Model

HuanjinYao/Mulberry_qwen2vl_7b

Model

HJYao00/Mulberry

[NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective…

1,243

HuanjinYao/Mulberry-SFT

Dataset

nyu-visionx/cambrian-8b

Model

llava-hf/llama3-llava-next-8b-hf

Model

aimagelab/LLaVA_MORE-llama_3_1-8B-S2-pretrain

Model

PrincetonPLI/Eagle-X2-Llama3-8B

Model

Linked in READMEs

HJYao00/Mulberry

[NIPS'25 Spotlight] Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective…

1,243

README badge

README

Mulberry

Mulberry-llava-8b is a step-by-step reasoning model trained on the Mulberry-260K SFT dataset, which was generated through collective knowledge search using CoMCTS.

For reasoning inference, please refer to our GitHub.

Paper: https://arxiv.org/abs/2412.18319

Code: https://github.com/HJYao00/Mulberry

More Details

Base Model: https://huggingface.co/llava-hf/llama3-llava-next-8b-hf

Training Framework: LLaMA-Factory

Hardware: 8x NVIDIA H100