anopska

arcee-trainium-recipes

The repository contains all the set-up required to execute trainium training jobs.

gorilla

Gorilla: An API store for LLMs

grammar-based-agents

Modular open LLM agents via prompt chaining and schema-guided generation

ipyexperiments

Automatic GPU+CPU memory profiling, re-use and memory leaks detection using jupyter/ipython experiment containers

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

NexusRaven

NexusRaven-13B, a new SOTA Open-Source LLM for function calling. This repo contains everything for reproducing our evaluation on NexusRaven-13B and baselines.

parallel-computing-tutorial

peft_lora

Repo accompanying PEFT/LoRA article.

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

anopska/arcee-trainium-recipes

The repository contains all the set-up required to execute trainium training jobs.

anopska/gorilla

Gorilla: An API store for LLMs

anopska/grammar-based-agents

Modular open LLM agents via prompt chaining and schema-guided generation

anopska/ipyexperiments

Automatic GPU+CPU memory profiling, re-use and memory leaks detection using jupyter/ipython experiment containers

anopska/llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

anopska/lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

anopska/NexusRaven

NexusRaven-13B, a new SOTA Open-Source LLM for function calling. This repo contains everything for reproducing our evaluation on NexusRaven-13B and baselines.

anopska/parallel-computing-tutorial

anopska/peft_lora

Repo accompanying PEFT/LoRA article.

anopska/qlora

QLoRA: Efficient Finetuning of Quantized LLMs

anopska/TinyChatEngine

TinyChatEngine: On-Device LLM Inference Library

anopska/tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

anopska/visualizing-finetunes

anopska/vllm

A high-throughput and memory-efficient inference and serving engine for LLMs