oKatanaaa / kolibrify
Curriculum training of instruction-following LLMs with Unsloth
☆14Updated last month
Alternatives and similar repositories for kolibrify:
Users that are interested in kolibrify are comparing it to the libraries listed below
- ☆113Updated 3 weeks ago
- Set of scripts to finetune LLMs☆37Updated last year
- ☆48Updated 5 months ago
- ☆41Updated 2 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆39Updated 2 months ago
- ☆75Updated last year
- Tokun to can tokens☆16Updated this week
- Submodule of evalverse forked from [google-research/instruction_following_eval](https://github.com/google-research/google-research/tree/m…☆13Updated 11 months ago
- ☆28Updated 5 months ago
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆121Updated last year
- ☆29Updated last month
- Simple Model Similarities Analysis☆21Updated last year
- Simple GRPO scripts and configurations.☆58Updated 2 months ago
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆36Updated 11 months ago
- ☆66Updated 11 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- Trully flash implementation of DeBERTa disentangled attention mechanism.☆45Updated 2 weeks ago
- minimal pytorch implementation of bm25 (with sparse tensors)☆101Updated last year
- ☆47Updated 8 months ago
- ☆24Updated last year
- LLM-Training-API: Including Embeddings & ReRankers, mergekit, LaserRMT☆27Updated last year
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆55Updated 7 months ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks☆31Updated 11 months ago
- experiments with inference on llama☆104Updated 10 months ago
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absolute…☆49Updated 9 months ago
- ☆20Updated last year
- A stable, fast and easy-to-use inference library with a focus on a sync-to-async API☆45Updated 7 months ago
- ☆17Updated 11 months ago
- This repository contains code for cleaning your training data of benchmark data to help combat data snooping.☆25Updated 2 years ago