ibibek Goto Github PK

lit-llama

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

llama-adapter

Fine-tuning LLaMA to follow instructions within 1 Hour and 1.2M Parameters

llama-viz

The attention map viewer for LLaMA models.

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

llm-conversation-safety

[NAACL2024] Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey

llm-latent-language

Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".

llm-nli-analysis

llms-finetuning-safety

We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.

lm-experiment

LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces

low-resrouce-dataset

malconv-deep-learning-for-pe-malware-classification

markdown-cheatsheet

Markdown Cheatsheet for Github Readme.md

mddial-med-dataset

mi-bci-csp

Implementing Common Spatial Pattern (CSP) algorithm for MI-BCI from scratch with python

ml-annotate

Use ML-Annotate to label data for machine learning purposes

mlx-examples

Examples in the MLX framework

mother-of-all-bci-benchmarks

Mother of All BCI Benchmarks

multilingual-safety-for-llms

Data for "Multilingual Jailbreak Challenges in Large Language Models"

nepali-alpaca-chatgpt

nepali-chat-gpt

neurotech-course

CS198-96: Intro to Neurotechnology @ UC Berkeley

ollama-server-docs

ongdb-graph-db

ONgDB is an independent fork of Neo4j® Enterprise Edition version 3.4.0.rc02 licensed under AGPLv3 and/or Community Edition licensed under GPLv3

phi2-finetune

presumm

code for EMNLP 2019 paper Text Summarization with Pretrained Encoders

privategpt

Interact privately with your documents using the power of GPT, 100% privately, no data leaks

prompt-injection-interp

promptbench

A unified evaluation framework for large language models

pytorch-llama

LLaMA 2 implemented from scratch in PyTorch

qameleon

QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning PaLM with only five examples per language. We use the synthetic data to finetune downstream QA models leading to improved accuracy in comparison to English-only and translation-based baselines.