okuvshynov / slowllama
Finetune llama2-70b and codellama on MacBook Air without quantization
☆448Updated 11 months ago
Alternatives and similar repositories for slowllama:
Users that are interested in slowllama are comparing it to the libraries listed below
- Visualize the intermediate output of Mistral 7B☆344Updated last month
- LLaMa retrieval plugin script using OpenAI's retrieval plugin☆324Updated last year
- Fine-tune mistral-7B on 3090s, a100s, h100s☆706Updated last year
- LLM Analytics☆645Updated 4 months ago
- JS tokenizer for LLaMA 1 and 2☆350Updated 8 months ago
- Neum AI is a best-in-class framework to manage the creation and synchronization of vector embeddings at large scale.☆853Updated last year
- A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for vario…☆1,006Updated 2 weeks ago
- Agents Capable of Self-Editing Their Prompts / Python Code☆756Updated 11 months ago
- An implementation of bucketMul LLM inference☆215Updated 8 months ago
- Fine-tune LLM agents with online reinforcement learning☆1,077Updated 11 months ago
- Complex LLM Workflows from Simple JSON.☆292Updated last year
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆279Updated 3 weeks ago
- A bagel, with everything.☆317Updated 11 months ago
- C++ implementation for 💫StarCoder☆452Updated last year
- Stateful load balancer custom-tailored for llama.cpp 🏓🦙☆717Updated this week
- ☆111Updated last month
- A simple "Be My Eyes" web app with a llama.cpp/llava backend☆490Updated last year
- Tune any FALCON in 4-bit☆466Updated last year
- Stop messing around with finicky sampling parameters and just use DRµGS!☆345Updated 9 months ago
- Finetune ALL LLMs with ALL Adapeters on ALL Platforms!☆314Updated last month
- Prompt engineering for developers☆677Updated last year
- fast vector database made in numpy☆752Updated 10 months ago
- ☆511Updated 6 months ago
- Inference code for Persimmon-8B☆416Updated last year
- A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and full…☆603Updated 3 months ago
- Instruct-tune LLaMA on consumer hardware☆362Updated last year
- Enforce structured output from LLMs 100% of the time☆247Updated 7 months ago
- batched loras☆338Updated last year
- Constrained Decoding for LLMs against JSON Schema☆326Updated last year
- llama3.np is a pure NumPy implementation for Llama 3 model.☆973Updated 9 months ago