Topic: transformer

A high-throughput and memory-efficient inference and serving engine for LLMs

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

Fully automatic censorship removal for language models

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Production First and Production Ready End-to-End Speech Recognition Toolkit

Scalable and user friendly neural :brain: forecasting algorithms.

基于深度强化学习的开源自动因子工厂。

MoBA: Mixture of Block Attention for Long-Context LLMs

Convert images of LaTex math equations into LaTex code.

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

A high-throughput and memory-efficient inference and serving engine for LLMs

Fully automatic censorship removal for language models

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

Production First and Production Ready End-to-End Speech Recognition Toolkit

Scalable and user friendly neural :brain: forecasting algorithms.