Mllm Python Packages

infinity-parser2

INF Tech's open-source MLLMs for SOTA visual-language understanding and advanced document intelligence.

flexllm

High-Performance LLM Client for Production Batch processing with checkpoint recovery, response caching, load balancing, and cost tracking

mantis-vl

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]

gui-agents

Agent S: an open agentic framework that uses computers like a human

nlp-shap

mllm-shap: Shapley-value explainability for conversational and multimodal language models.

mllm-shap

mllm-shap: Shapley-value explainability for conversational and multimodal language models.

roboml

RoboML is an aggregator package written for prototyping and deploying open source ML models for robotics

freegpthub-dramamoyu

FreeGPTHub: A truly free, unified GPT API gateway—unlike “fake-free” alternatives that hide paywalls behind quotas, trials, or mandatory top-ups. (真正免费的GPT统一接口，支持讯飞星火知识大模型，百度文心大模型，OpenAI ChatGPT，智谱大模型，幻方量化深度求索，字节豆包，阿里通义千问，稀宇科技MiniMax，魔搭社区开源模型等)

freegpthub

FreeGPTHub: A truly free, unified GPT API gateway—unlike “fake-free” alternatives that hide paywalls behind quotas, trials, or mandatory top-ups. (真正免费的GPT统一接口，支持讯飞星火知识大模型，百度文心大模型，OpenAI ChatGPT，智谱大模型，幻方量化深度求索，字节豆包，阿里通义千问，稀宇科技MiniMax，魔搭社区开源模型等)

deco-mllm

[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

unipercept-reward

[ICML2026 Spotlight] UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture

eagle-embodied

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

vt-calc

🧮 Calculator for vision tokens in VLMs.

openemma

OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.