SqueezeAILab / TinyAgent
TinyAgent: Function Calling at the Edge!
☆124Updated 2 weeks ago
Related projects: ⓘ
- ☆242Updated 2 weeks ago
- CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/☆167Updated this week
- Official Implementation of "Multi-Head RAG: Solving Multi-Aspect Problems with LLMs"☆155Updated 2 months ago
- ☆111Updated 3 months ago
- AWM: Agent Workflow Memory☆121Updated last week
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and …☆313Updated 3 months ago
- A simple unified framework for evaluating LLMs☆121Updated this week
- ☆262Updated this week
- Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"☆439Updated 6 months ago
- Long context evaluation for large language models☆148Updated this week
- The official evaluation suite and dynamic data release for MixEval.☆200Updated last week
- Code for the paper 🌳 Tree Search for Language Model Agents☆124Updated last month
- Benchmarks, environments, and toolkits for general computer agents☆154Updated this week
- An Open Source Toolkit For LLM Distillation☆284Updated last month
- ☆109Updated last month
- Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"☆264Updated 9 months ago
- ☆90Updated last month
- NexusRaven-13B, a new SOTA Open-Source LLM for function calling. This repo contains everything for reproducing our evaluation on NexusRav…☆304Updated 11 months ago
- Expert Specialized Fine-Tuning☆129Updated last month
- ☆82Updated 3 weeks ago
- Banishing LLM Hallucinations Requires Rethinking Generalization☆253Updated 2 months ago
- This is work done by the Oxen.ai Community, trying to reproduce the Self-Rewarding Language Model paper from MetaAI.☆99Updated 4 months ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆218Updated 5 months ago
- Official repo for "Make Your LLM Fully Utilize the Context"☆239Updated 4 months ago
- WebLINX is a benchmark for building web navigation agents with conversational capabilities☆111Updated 2 months ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆158Updated 2 months ago
- Official implementation for the paper "LongEmbed: Extending Embedding Models for Long Context Retrieval"☆108Updated 4 months ago
- An implemtation of Everyting of Thoughts (XoT).☆114Updated 7 months ago
- awesome synthetic (text) datasets☆213Updated last week
- [ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning☆309Updated 2 weeks ago