facebookresearch / MobileLLM
MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.
☆1,217Updated last month
Alternatives and similar repositories for MobileLLM:
Users that are interested in MobileLLM are comparing it to the libraries listed below
- Everything about the SmolLM & SmolLM2 family of models☆1,554Updated last week
- MINT-1T: A one trillion token multimodal interleaved dataset.☆788Updated 5 months ago
- Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"☆831Updated last month
- nanoGPT style version of Llama 3.1☆1,290Updated 5 months ago
- DataComp for Language Models☆1,206Updated last month
- Distributed Training Over-The-Internet☆857Updated last month
- Recipes to scale inference-time compute of open models☆932Updated this week
- Code for BLT research paper☆1,314Updated this week
- Minimalistic large language model 3D-parallelism training☆1,386Updated this week
- Reaching LLaMA2 Performance with 0.1M Dollars☆965Updated 5 months ago
- A PyTorch native library for large model training☆3,091Updated this week
- [NeurIPS'24 Spotlight] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces in…☆874Updated 2 weeks ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆732Updated this week
- ☆2,289Updated this week
- An Open Large Reasoning Model for Real-World Solutions☆1,378Updated last month
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆561Updated this week
- Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.☆1,908Updated 5 months ago
- 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
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆2,669Updated last week
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆970Updated this week
- ☆664Updated this week
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,371Updated 6 months ago
- Janus-Series: Unified Multimodal Understanding and Generation Models☆1,327Updated 2 months ago
- PyTorch native quantization and sparsity for training and inference☆1,753Updated this week
- llama3.np is a pure NumPy implementation for Llama 3 model.☆975Updated 7 months ago
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,462Updated this week
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,481Updated 2 months ago
- TinyChatEngine: On-Device LLM Inference Library☆792Updated 6 months ago
- Training LLMs with QLoRA + FSDP☆1,436Updated 2 months ago