broskicodes / slms
Experimenting with small language models
☆62Updated last year
Alternatives and similar repositories for slms:
Users that are interested in slms are comparing it to the libraries listed below
- Video+code lecture on building nanoGPT from scratch☆65Updated 8 months ago
- entropix style sampling + GUI☆25Updated 3 months ago
- ☆123Updated 5 months ago
- Easy to use, High Performant Knowledge Distillation for LLMs☆45Updated last month
- Set of scripts to finetune LLMs☆36Updated 10 months ago
- Dataset Crafting w/ RAG/Wikipedia ground truth and Efficient Fine-Tuning Using MLX and Unsloth. Includes configurable dataset annotation …☆169Updated 6 months ago
- LLM-Training-API: Including Embeddings & ReRankers, mergekit, LaserRMT☆26Updated 11 months ago
- Using open source LLMs to build synthetic datasets for direct preference optimization☆57Updated 11 months ago
- customizable template GPT code designed for easy novel architecture experimentation☆26Updated 3 months ago
- ☆112Updated 4 months ago
- run ollama & gguf easily with a single command☆49Updated 9 months ago
- ☆108Updated 5 months ago
- Let's create synthetic textbooks together :)☆73Updated last year
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absolute…☆48Updated 7 months ago
- 1.58-bit LLaMa model☆81Updated 10 months ago
- Testing LLM reasoning abilities with family relationship quizzes.☆57Updated 2 weeks ago
- ☆121Updated 3 weeks ago
- Fully fine-tune large models like Mistral, Llama-2-13B, or Qwen-14B completely for free☆230Updated 3 months ago
- Various installation guides for Large Language Models☆62Updated 3 months ago
- An easy-to-understand framework for LLM samplers that rewind and revise generated tokens☆129Updated last week
- ☆41Updated last week
- The simplest, fastest repository for training/finetuning medium-sized xLSTMs.☆39Updated 8 months ago
- Locally running LLM with internet access☆93Updated 3 months ago
- Some simple scripts that I use day-to-day when working with LLMs and Huggingface Hub☆156Updated last year
- ☆111Updated last month
- ☆32Updated 2 weeks ago
- RAFT, or Retrieval-Augmented Fine-Tuning, is a method comprising of a fine-tuning and a RAG-based retrieval phase. It is particularly sui…☆85Updated 5 months ago
- A stable, fast and easy-to-use inference library with a focus on a sync-to-async API☆44Updated 4 months ago
- ☆83Updated 3 weeks ago