Skip to content

PaperCodex

Subscribe

Text Generation

GLM-130B: A Truly Open, Bilingual 130B-Language Model That Runs on Consumer GPUs

GLM-130B: A Truly Open, Bilingual 130B-Language Model That Runs on Consumer GPUs 7680

If you’re evaluating large language models (LLMs) for real-world deployment—especially in multilingual settings—you’ve likely hit a wall: most top-performing models…

01/05/2026Bilingual Language Modeling, Text Generation, Zero-shot Inference
TinyLlama: A Fast, Efficient 1.1B Open Language Model for Edge Deployment and Speculative Decoding

TinyLlama: A Fast, Efficient 1.1B Open Language Model for Edge Deployment and Speculative Decoding 8770

TinyLlama is a compact yet powerful open-source language model with just 1.1 billion parameters—but trained on an impressive 3 trillion…

12/22/2025On-device Inference, Speculative Decoding, Text Generation
TextBox 2.0: A Unified Library for Rapid Text Generation with Pre-Trained Language Models

TextBox 2.0: A Unified Library for Rapid Text Generation with Pre-Trained Language Models 1096

If you’ve ever struggled to compare BART, T5, and a custom Chinese language model on summarization, translation, or dialogue generation—only…

12/22/2025Machine Translation, Summarization, Text Generation
llama.cpp: Run Large Language Models Anywhere—Fast, Lightweight, and Offline

llama.cpp: Run Large Language Models Anywhere—Fast, Lightweight, and Offline 91182

In an era where large language models (LLMs) power everything from chatbots to code assistants, deploying them outside of cloud…

12/12/202512/15/2025Multimodal Inference, Offline LLM Deployment, Text Generation
BitNet: Run 1.58-Bit LLMs Locally on CPUs with 6x Speedup and 82% Less Energy

BitNet: Run 1.58-Bit LLMs Locally on CPUs with 6x Speedup and 82% Less Energy 24452

Running large language models (LLMs) used to require powerful GPUs, expensive cloud infrastructure, or specialized hardware—until BitNet changed the game.…

12/12/2025Efficient LLM Deployment, On-device Inference, Text Generation
Copyright © 2026 PaperCodex.
  • Facebook
  • YouTube
  • Twitter

PaperCodex