cooper12121 / llama3-8x8b-MoELinks
Copy the MLP of llama3 8 times as 8 experts , created a router with random initialization,add load balancing loss to construct an 8x8b MoE model based on llama3.
☆27Updated last year
Alternatives and similar repositories for llama3-8x8b-MoE
Users that are interested in llama3-8x8b-MoE are comparing it to the libraries listed below
Sorting:
- ☆53Updated last year
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆118Updated 7 months ago
- ☆50Updated last year
- ☆57Updated 5 months ago
- FuseAI Project☆88Updated 11 months ago
- SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning. COLM 2024 Accepted Paper☆32Updated last year
- Automatic prompt optimization framework for multi-step agent tasks.☆36Updated last year
- ☆36Updated last year
- Reformatted Alignment☆111Updated last year
- [ICLR 2025] LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization☆43Updated 10 months ago
- ☆93Updated 7 months ago
- [ICML'24] The official implementation of “Rethinking Optimization and Architecture for Tiny Language Models”☆126Updated 11 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)☆147Updated last year
- The source code and dataset mentioned in the paper Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmar…☆53Updated last year
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Updated last year
- Official completion of “Training on the Benchmark Is Not All You Need”.☆38Updated last year
- Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper☆151Updated last year
- code for Scaling Laws of RoPE-based Extrapolation☆73Updated 2 years ago
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆222Updated 5 months ago
- ☆95Updated last year
- This is a personal reimplementation of Google's Infini-transformer, utilizing a small 2b model. The project includes both model and train…☆58Updated last year
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆40Updated 2 years ago
- We aim to provide the best references to search, select, and synthesize high-quality and large-quantity data for post-training your LLMs.☆61Updated last year
- ☆104Updated last year
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆81Updated 2 weeks ago
- ☆62Updated last year
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆138Updated last year
- ☆124Updated last year
- ☆94Updated last year
- RewardAnything: Generalizable Principle-Following Reward Models☆45Updated 6 months ago