#large-language-models Repositories
1,249 repositories total
Explore a comprehensive collection of resources, tutorials, papers, tools, and best practices for fine-tuning Large Language Models (LLMs). Perfect for ML practitioners and researchers!
ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate
Krasis is a Hybrid LLM runtime which focuses on efficient running of larger models on consumer grade VRAM limited hardware
๐ Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
Prompts published by the public account Write Prompt, synchronously recorded here
Can large language models provide useful feedback on research papers? A large-scale empirical analysis.
PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. ๐ Best Paper Awards @ NeurIPS ML Safety Workshop 2022
a free and open-source browser sidebar plugin that offers a cost-free alternative to products like Sider, Monica, and Merlin.
[BIONLP@ACL 2024] XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Models.
[NeurIPS 2023] Official implementations of "Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models"
[ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.
Learn LLM Inference Engineering step by stepโfrom KV cache, PagedAttention, and continuous batching to vLLM, SGLang, and GPUs.
๐๐๐ [ICML 2026] Official Implementation of Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
Keep track of big models in audio domain, including speech, singing, music etc.
[ACL 2025 Demo] Repository for the demo and paper: ReasonGraph: Visualisation of Reasoning Paths
Official Implementation of ICLR 2024 paper: "Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning"
YouDub is an open-source tool designed to automatically translate and dub high-quality YouTube videos, enabling them to be ported onto the Chinese internet. The tool uses AI speech recognition technology to convert audio into text, then translates the text into Chinese using a Large Language Model (LLM), and finally converts the Chinese text back into audio using AI voice cloning technology. This allows us to create Chinese-dubbed videos that retain the original YouTuber's voice tone.
๐ฅ๐ฅ๐ฅ[AAAI 2026 Oral] Official Implementation of RobustโR1: DegradationโAware Reasoning for Robust Visual Understanding
A tool for translating the content of LaTeX documents into various other natural languages (e.g., translating an arXiv paper from English to Chinese).
tracking papers, datasets, and models of "large language model (LLM) for time series"
Closed-source semi-automatic vulnerability discovery tool, performs static code analysis on jar/war/zip, outputting reachable paths from source to sink. The LLM will verify path reachability and provide a confidence score for the path based on context.
Papers and Datasets on Instruction Tuning and Following. โจโจโจ
[EMNLP 2023] Enabling Large Language Models to Generate Text with Citations. Paper: https://arxiv.org/abs/2305.14627
A library for easily merging multiple LLM experts, and efficiently train the merged LLM.