Mihaiii / backtrack_samplerLinks
An easy-to-understand framework for LLM samplers that rewind and revise generated tokens
☆150Updated 3 weeks ago
Alternatives and similar repositories for backtrack_sampler
Users that are interested in backtrack_sampler are comparing it to the libraries listed below
Sorting:
- Low-Rank adapter extraction for fine-tuned transformers models☆180Updated last year
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆175Updated last year
- an implementation of Self-Extend, to expand the context window via grouped attention☆119Updated 2 years ago
- ☆137Updated last year
- smolLM with Entropix sampler on pytorch☆149Updated last year
- ☆68Updated last year
- Just a bunch of benchmark logs for different LLMs☆119Updated last year
- ☆140Updated 5 months ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆183Updated 2 months ago
- Generate Synthetic Data Using OpenAI, MistralAI or AnthropicAI☆222Updated last year
- An introduction to LLM Sampling☆79Updated last year
- This is our own implementation of 'Layer Selective Rank Reduction'☆240Updated last year
- Simple GRPO scripts and configurations.☆59Updated 11 months ago
- Train your own SOTA deductive reasoning model☆107Updated 10 months ago
- entropix style sampling + GUI☆27Updated last year
- Official repo for Learning to Reason for Long-Form Story Generation☆74Updated 9 months ago
- ☆120Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 3 months ago
- ☆165Updated 5 months ago
- Mixing Language Models with Self-Verification and Meta-Verification☆112Updated last year
- Using open source LLMs to build synthetic datasets for direct preference optimization☆72Updated last year
- ☆119Updated last year
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆109Updated 8 months ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆232Updated last year
- Easy to use, High Performant Knowledge Distillation for LLMs☆97Updated 8 months ago
- Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first app…☆169Updated 2 years ago
- ☆74Updated 2 years ago
- Lego for GRPO☆30Updated 8 months ago
- Evaluating LLMs with CommonGen-Lite☆93Updated last year
- EvaByte: Efficient Byte-level Language Models at Scale☆115Updated 9 months ago