Alternatives and similar repositories for CoSMIC

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

• unslothai / unsloth
  Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
  ☆51,625Updated this week
• unslothai / notebooks
  100+ Fine-tuning Tutorial Notebooks on Google Colab, Kaggle and more.
  ☆4,015Updated this week
• Kamil-Sabbagh / Data-Knowledge-Representation
  ☆11Updated last year
• pytorch / torchchat
  Run PyTorch LLMs locally on servers, desktop and mobile
  ☆3,624Updated 5 months ago
• mlabonne / llm-datasets
  Curated list of datasets and tools for post-training.
  ☆4,229Updated 3 months ago
• Wan-Video / Wan2.1
  Wan: Open and Advanced Large-Scale Video Generative Models
  ☆15,294Updated last month
• meta-pytorch / torchtune
  PyTorch native post-training library
  ☆5,669Updated this week
• santiagourregobotero / FileDownloader
  ☆16Updated 2 years ago
• OpenGVLab / InternVL
  [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
  ☆9,792Updated 4 months ago
• naklecha / llama3-from-scratch
  llama3 implementation one matrix multiplication at a time
  ☆15,241Updated last year
• ollama / ollama-python
  Ollama Python library
  ☆9,292Updated 2 weeks ago
• Wan-Video / Wan2.2
  Wan: Open and Advanced Large-Scale Video Generative Models
  ☆14,122Updated last month
• prijall / DeepLearning
  This Repository contains work/learning related to Deep Learning!
  ☆13Updated 3 months ago
• facebookresearch / large_concept_model
  Large Concept Models: Language modeling in a sentence representation space
  ☆2,332Updated last year
• ashishpatel26 / LLM-Finetuning
  LLM Finetuning with peft
  ☆2,767Updated 6 months ago
• lyogavin / airllm
  AirLLM 70B inference with single 4GB GPU
  ☆11,052Updated 5 months ago
• QwenLM / Qwen-Agent
  Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
  ☆13,234Updated last week
• microsoft / BitNet
  Official inference framework for 1-bit LLMs
  ☆28,054Updated last week
• Lightricks / LTX-Video
  Official repository for LTX-Video
  ☆9,235Updated last month
• bytedance / UI-TARS
  Pioneering Automated GUI Interaction with Native Agents
  ☆9,343Updated 2 weeks ago
• Lightning-AI / LitServe
  A minimal Python framework for building custom AI inference servers with full control over logic, batching, and scaling.
  ☆3,802Updated this week
• ItzCrazyKns / Perplexica
  Perplexica is an AI-powered answering engine.
  ☆28,711Updated last month
• black-forest-labs / flux
  Official inference repo for FLUX.1 models
  ☆25,187Updated 6 months ago
• QwenLM / Qwen3-VL
  Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆18,178Updated last week
• policy-gradient / GRPO-Zero
  Implementing DeepSeek R1's GRPO algorithm from scratch
  ☆1,762Updated 9 months ago
• topoteretes / cognee
  Memory for AI Agents in 6 lines of code
  ☆11,703Updated this week
• confident-ai / deepeval
  The LLM Evaluation Framework
  ☆13,435Updated this week
• 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…
  ☆3,084Updated 2 weeks ago
• QwenLM / Qwen3
  Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
  ☆26,530Updated last month
• dsgiitr / ForecastPro
  Tensorflow-Based Approach to Handling Single-Step and Iterated Forecasting
  ☆10Updated last year