axolotl-ai-cloud / axolotl-cookbookLinks
☆35Updated 2 months ago
Alternatives and similar repositories for axolotl-cookbook
Users that are interested in axolotl-cookbook are comparing it to the libraries listed below
Sorting:
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆55Updated 8 months ago
- Train your own SOTA deductive reasoning model☆107Updated 6 months ago
- ☆54Updated 10 months ago
- Matrix (Multi-Agent daTa geneRation Infra and eXperimentation framework) is a versatile engine for multi-agent conversational data genera…☆94Updated this week
- Simple GRPO scripts and configurations.☆59Updated 7 months ago
- Lego for GRPO☆29Updated 4 months ago
- look how they massacred my boy☆63Updated 11 months ago
- Official homepage for "Self-Harmonized Chain of Thought" (NAACL 2025)☆91Updated 8 months ago
- ☆135Updated last year
- Source code for the collaborative reasoner research project at Meta FAIR.☆103Updated 5 months ago
- ☆136Updated last month
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 10 months ago
- Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya☆116Updated last month
- ☆68Updated 4 months ago
- ☆67Updated last year
- ☆40Updated last year
- Code for our paper PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles☆55Updated 4 months ago
- An introduction to LLM Sampling☆79Updated 9 months ago
- ☆119Updated last year
- entropix style sampling + GUI☆27Updated 11 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆17Updated 11 months ago
- ☆13Updated 5 months ago
- Code for ExploreTom☆86Updated 3 months ago
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆172Updated 8 months ago
- Luth is a state-of-the-art series of fine-tuned LLMs for French☆33Updated this week
- High level library for batched embeddings generation, blazingly-fast web-based RAG and quantized indexes processing ⚡☆67Updated 11 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆24Updated 2 weeks ago
- A Qwen .5B reasoning model trained on OpenR1-Math-220k☆14Updated 7 months ago
- GPT-4 Level Conversational QA Trained In a Few Hours☆64Updated last year