Stars
Chat Templates for 🤗 HuggingFace Large Language Models
Official style files for papers submitted to venues of the Association for Computational Linguistics
The official implementation of Self-Play Fine-Tuning (SPIN)
中文大模型能力评测榜单：目前已囊括115个大模型，覆盖chatgpt、gpt4o、百度文心一言、阿里通义千问、讯飞星火、商汤senseChat、minimax等商用模型， 以及百川、qwen2、glm4、yi、书生internLM2、llama3等开源大模型，多维度能力评测。不仅提供能力评分排行榜，也提供所有模型的原始输出结果！
📖 A curated list of resources dedicated to hallucination of multimodal large language models (MLLM).
Representation Engineering: A Top-Down Approach to AI Transparency
[DMLR 2024] Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift
The code and datasets of our ACM MM 2024 paper "Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs".
📰 Must-read papers and blogs on Speculative Decoding ⚡️
A novel approach to improve the safety of large language models, enabling them to transition effectively from unsafe to safe state.
Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.
Persuasive Jailbreaker: we can persuade LLMs to jailbreak them!
Train transformer language models with reinforcement learning.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Foundational Models for State-of-the-Art Speech and Text Translation
Doing simple retrieval from LLM models at various context lengths to measure accuracy
A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.
A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/
Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting
The implement of ACL2024: "MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization"
Exploring CoT-Decoding from Google DeepMind's paper, "Chain-of-Thought Reasoning Without Prompting".
An Attentive Neural Sequence Labeling Model for Adverse Drug Reactions Mentions Extraction
[NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey