facebookresearch / MobileLLMLinks
MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.
☆1,301Updated 2 months ago
Alternatives and similar repositories for MobileLLM
Users that are interested in MobileLLM are comparing it to the libraries listed below
Sorting:
- nanoGPT style version of Llama 3.1☆1,380Updated 10 months ago
- DataComp for Language Models☆1,309Updated 3 months ago
- [ICLR 2025] Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling☆881Updated last month
- Minimalistic large language model 3D-parallelism training☆1,926Updated last week
- Everything about the SmolLM2 and SmolVLM family of models☆2,574Updated 2 months ago
- Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM☆1,500Updated this week
- MINT-1T: A one trillion token multimodal interleaved dataset.☆817Updated 10 months ago
- Code for BLT research paper☆1,683Updated 3 weeks ago
- Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.☆2,016Updated 10 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,055Updated this week
- TinyChatEngine: On-Device LLM Inference Library☆861Updated 11 months ago
- Official implementation of Half-Quadratic Quantization (HQQ)☆827Updated last week
- Recipes to scale inference-time compute of open models☆1,095Updated 3 weeks ago
- Open weights language model from Google DeepMind, based on Griffin.☆641Updated 2 weeks ago
- Reaching LLaMA2 Performance with 0.1M Dollars☆982Updated 10 months ago
- PyTorch native quantization and sparsity for training and inference☆2,114Updated this week
- ☆4,084Updated last year
- [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration☆3,081Updated last week
- Official inference library for pre-processing of Mistral models☆742Updated this week
- NanoGPT (124M) in 3 minutes☆2,660Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆2,757Updated last week
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,835Updated last year
- Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends☆1,629Updated this week
- An Open Large Reasoning Model for Real-World Solutions☆1,497Updated 3 weeks ago
- VPTQ, A Flexible and Extreme low-bit quantization algorithm☆642Updated last month
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,593Updated last month
- ☆541Updated 9 months ago
- Muon is Scalable for LLM Training☆1,077Updated 2 months ago
- AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:☆2,193Updated last month
- Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads☆2,549Updated 11 months ago