mistralai / megablocks-publicView external linksLinks
☆867Dec 8, 2023Updated 2 years ago
Alternatives and similar repositories for megablocks-public
Users that are interested in megablocks-public are comparing it to the libraries listed below
Sorting:
- Inference code for Mistral and Mixtral hacked up into original Llama implementation☆369Dec 9, 2023Updated 2 years ago
- A family of open-sourced Mixture-of-Experts (MoE) Large Language Models☆1,657Mar 8, 2024Updated last year
- Official inference library for Mistral models☆10,664Nov 21, 2025Updated 2 months ago
- Tools for merging pretrained large language models.☆6,783Jan 26, 2026Updated 2 weeks ago
- YaRN: Efficient Context Window Extension of Large Language Models☆1,669Apr 17, 2024Updated last year
- [ICLR 2024] Efficient Streaming Language Models with Attention Sinks☆7,188Jul 11, 2024Updated last year
- Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.☆6,183Aug 22, 2025Updated 5 months ago
- Minimalistic large language model 3D-parallelism training☆2,544Dec 11, 2025Updated 2 months ago
- Robust recipes to align language models with human and AI preferences☆5,495Sep 8, 2025Updated 5 months ago
- Go ahead and axolotl questions☆11,289Updated this week
- Examples in the MLX framework☆8,238Updated this week
- ⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Pl…☆2,174Oct 8, 2024Updated last year
- Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.☆10,309Jul 1, 2024Updated last year
- LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath☆9,477Jun 7, 2025Updated 8 months ago
- The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.☆8,891May 3, 2024Updated last year
- OpenChat: Advancing Open-source Language Models with Imperfect Data☆5,472Sep 13, 2024Updated last year
- Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.☆2,085Jul 29, 2024Updated last year
- Ongoing research training transformer models at scale☆38Jan 19, 2024Updated 2 years ago
- [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding☆1,316Mar 6, 2025Updated 11 months ago
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters☆1,897Jan 21, 2024Updated 2 years ago
- A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)☆4,742Jan 8, 2024Updated 2 years ago
- Run Mixtral-8x7B models in Colab or consumer desktops☆2,325Apr 8, 2024Updated last year
- A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI☆771Dec 15, 2023Updated 2 years ago
- ☆415Nov 2, 2023Updated 2 years ago
- Just a bunch of benchmark logs for different LLMs☆119Jul 28, 2024Updated last year
- 20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.☆13,155Feb 8, 2026Updated last week
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,234May 8, 2024Updated last year
- Salesforce open-source LLMs with 8k sequence length.☆724Jan 31, 2025Updated last year
- QLoRA: Efficient Finetuning of Quantized LLMs☆10,835Jun 10, 2024Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆279Nov 3, 2023Updated 2 years ago
- Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients.☆201Jul 17, 2024Updated last year
- inference code for mixtral-8x7b-32kseqlen☆105Dec 12, 2023Updated 2 years ago
- Fast and memory-efficient exact attention☆22,231Updated this week
- Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.☆2,885Updated this week
- ☆8,672Oct 9, 2024Updated last year
- The RedPajama-Data repository contains code for preparing large datasets for training large language models.☆4,924Dec 7, 2024Updated last year
- ☆593Aug 23, 2024Updated last year
- OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset☆7,530Jul 16, 2023Updated 2 years ago
- Reaching LLaMA2 Performance with 0.1M Dollars☆987Jul 23, 2024Updated last year