Alternatives and similar repositories for smollm:

Users that are interested in smollm are comparing it to the libraries listed below

• dleemiller / WordLlama
  Things you can do with the token embeddings of an LLM
  ☆1,411Updated last week
• facebookresearch / MobileLLM
  MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.
  ☆1,217Updated last month
• janhq / ichigo
  Local realtime voice AI
  ☆2,162Updated this week
• Thytu / Agentarium
  open-source framework for creating and managing simulations populated with AI-powered agents. It provides an intuitive platform for desig…
  ☆837Updated last week
• chonkie-ai / chonkie
  🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library
  ☆2,249Updated this week
• codelion / optillm
  Optimizing inference proxy for LLMs
  ☆1,926Updated this week
• PaulPauls / llama3_interpretability_sae
  A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…
  ☆605Updated last month
• huggingface / huggingface-llama-recipes
  ☆590Updated last month
• pytorch / torchchat
  Run PyTorch LLMs locally on servers, desktop and mobile
  ☆3,462Updated this week
• merveenoyan / smol-vision
  Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜
  ☆1,093Updated 3 weeks ago
• Blaizzy / mlx-vlm
  MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
  ☆706Updated this week
• lm-sys / RouteLLM
  A framework for serving and evaluating LLM routers - save LLM costs without compromising quality
  ☆3,442Updated 5 months ago
• mistralai / mistral-common
  ☆664Updated this week
• ictnlp / LLaMA-Omni
  LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve spee…
  ☆2,746Updated 2 months ago
• lmnr-ai / flow
  A lightweight task engine for building stateful AI agents that prioritizes simplicity and flexibility.
  ☆837Updated last week
• AnswerDotAI / rerankers
  A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
  ☆1,238Updated last month
• argilla-io / distilabel
  Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…
  ☆1,879Updated this week
• AnswerDotAI / ModernBERT
  Bringing BERT into modernity via both architecture changes and scaling
  ☆1,045Updated last week
• karpathy / nano-llama31
  nanoGPT style version of Llama 3.1
  ☆1,290Updated 5 months ago
• illuin-tech / colpali
  The code used to train and run inference with the ColPali architecture.
  ☆1,386Updated this week
• KellerJordan / modded-nanogpt
  NanoGPT (124M) in 3.4 minutes
  ☆2,068Updated last week
• labmlai / inspectus
  LLM Analytics
  ☆634Updated 2 months ago
• mistralai / mistral-finetune
  ☆2,802Updated 4 months ago
• facebookresearch / large_concept_model
  Large Concept Models: Language modeling in a sentence representation space
  ☆1,713Updated this week
• felafax / felafax
  Felafax is building AI infra for non-NVIDIA GPUs
  ☆551Updated this week
• circlemind-ai / fast-graphrag
  RAG that intelligently adapts to your use case, data, and queries
  ☆2,747Updated this week
• likejazz / llama3.np
  llama3.np is a pure NumPy implementation for Llama 3 model.
  ☆975Updated 7 months ago
• neural-maze / agentic_patterns
  Implementing the 4 agentic patterns from scratch
  ☆973Updated 2 months ago
• mistralai / cookbook
  ☆1,403Updated last week
• AnswerDotAI / byaldi
  Use late-interaction multi-modal models such as ColPali in just a few lines of code.
  ☆693Updated 2 months ago