Ken aka Frosty's repositories
awesome-llm-interpretability
A curated list of Large Language Model (LLM) Interpretability resources.
axolotl
Go ahead and axolotl questions
deepsparse
Sparsity-aware deep learning inference runtime for CPUs
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
gateway
A Blazing Fast AI Gateway. Route to 100+ LLMs with 1 fast & friendly API.
laser
The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
llama-tokenizer-js
JS tokenizer for LLaMA
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
LLM-Shearing
Preprint: Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
mergekit
Tools for merging pretrained large language models.
meta-llama
Inference code for LLaMA models
NEFTune
Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning
onnx-model-zoo
A collection of pre-trained, state-of-the-art models in the ONNX format
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Orion
Orion-14B is a family of models includes a 14B foundation LLM, and a series of models: a chat model, a long context model, a quantized model, a RAG fine-tuned model, and an Agent fine-tuned model. Orion-14B 系列模型包括一个具有140亿参数的多语言基座大模型以及一系列相关的衍生模型，包括对话模型，长文本模型，量化模型，RAG微调模型，Agent微调模型等。
skypilot
SkyPilot: Run LLMs, AI, and Batch jobs on any cloud. Get maximum savings, highest GPU availability, and managed execution—all with a simple interface.
sparseml
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
sparsify
ML model optimization product to accelerate inference.
table-transformer
Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS evaluation metric.
TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
unredacter
Never ever ever use pixelation as a redaction technique
unsloth
5X faster 60% less memory QLoRA finetuning