l0he1g

l0he1g's Stars

• unslothai/unsloth

  Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

  Language:Python19.7k1341.2k1.4k

• netease-youdao/QAnything

  Question and Answer based on Anything.

  Language:Python12.1k1064381.2k

• Unstructured-IO/unstructured

  Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

  Language:HTML9.6k631.1k804

• explodinggradients/ragas

  Supercharge Your LLM Application Evaluations 🚀

  Language:Python7.7k37889782

• run-llama/rags

  Build ChatGPT over your data, all with natural language

  Language:Python6.4k5840651

• mlfoundations/open_flamingo

  An open-source framework for training large multimodal models.

  Language:Python3.8k48176287

• weaigc/bingo

  Bingo，一个让你呼吸顺畅 New Bing。

  Language:TypeScript2.9k371421.3k

• openai/weak-to-strong

  Language:Python2.5k3317310

• truera/trulens

  Evaluation and Tracking for LLM Experiments

  Language:Python2.2k19304197

• ha0z1/New-Bing-Anywhere

  💬 New-Bing-Anywhere extension's source Always use Bing GPT-4

  Language:TypeScript2.2k16360134

• Tongji-KGLLM/RAG-Survey

  1.9k3318125

• deepseek-ai/DeepSeek-LLM

  DeepSeek LLM: Let there be answers

  Language:Makefile1.5k2733100

• stanford-oval/WikiChat

  WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.

  Language:Python1.2k1827108

• zjunlp/KnowledgeEditingPapers

  Must-read Papers on Knowledge Editing for Large Language Models.

  96827864

• ContextualAI/HALOs

  A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

  Language:Python76882447

• TencentARC/LLaMA-Pro

  [ACL 2024] Progressive LLaMA with Block Expansion.

  Language:Python488203236

• wangcunxiang/LLM-Factuality-Survey

  The repository for the survey paper <<Survey on Large Language Models Factuality: Knowledge, Retrieval and Domain-Specificity>>

  3304429

• shmsw25/FActScore

  A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"

  Language:Python30543647

• ofirpress/self-ask

  Code and data for "Measuring and Narrowing the Compositionality Gap in Language Models"

  Language:Jupyter Notebook3036433

• Re-Align/URIAL

  Language:Python2982718

• lm-sys/llm-decontaminator

  Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

  Language:Python2953623

• fenwii/huaweimind

  华为视角看世界，任总思维看问题，华为任正非**之路，Huawei Renzhengfei speech,email& article,整理自1994年开始的讲话稿，涉及财经、人力资源、战略、内控与公共关系，从交换机、通讯设备、移动终端到人工智能、物联网，从2G、3G到4G、5G，从物理学、化学、数学到心理学、哲学，是创业，学习的标杆素材。

  289131122

• StonyBrookNLP/ircot

  Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23

  Language:Jsonnet181212822

• AlexTMallen/adaptive-retrieval

  Language:Python172279

• liziniu/ReMax

  Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)

  Language:Python1552313

• thu-coai/CritiqueLLM

  Language:Python132274

• snu-mllab/DPPO

  Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)

  Language:Python39221

• liziniu/policy_optimization

  Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)

  Language:Python24105

• syncdoth/Chain-of-Hindsight-PyTorch

  Unofficial implementation of Chain of Hindsight (https://arxiv.org/abs/2302.02676) using pytorch and huggingface Trainers.

  Language:Python11212

• najoungkim/QAQA

  Repository for the paper (QA)^2: Question Answering with Questionable Assumptions

  9200