Skip to main content
Advanced Search
Search Terms
Content Type

Exact Matches
Tag Searches
Date Options
Updated after
Updated before
Created after
Created before

Search Results

36 total results found

Japanese LLMs


There has been a stream of open Japanese LLMs being trained but they are on average far behind their English counterparts. The current most promising open model for conversation and instruction are the ELYZA Llama2-based models. GPT-4 and gpt-3.5-turbo are sti...


LLMs Quantization

Summary OmniQuant (omnidirectionally calibrated quantization) is a quantization technique published (2023-08-25) by Wenqi Shao and Mengzhao Chen from the General Vision Group, Shanghai AI Lab. Instead of hand-crafted quantization parameters, OmniQuant uses tra...

OpenAI API Compatibility


Most inferencing packages have their own REST API, but having an OpenAI compatible API is useful for using a variety of clients, or to be able to easily switch between providers. General llama.cpp Python wrapp...



Prompting Prompt Format Most instruct/chat fine tunes u...



Google MADLAD-400 10.7B model NLLB 54B model https://w...


LLMs Research

Language Models Implement Simple Word2Vec-styleVector Arithmetic

Fine Tuning Mistral


We'll try to fine tune Mistral 7B. Training Details The Mistral AI Discord has a #finetuning channel which has some info/discussion: dhokas: here are the main parameters we used for the instruct model : optimizer: adamw, max_lr: 2.5e-5, warmup steps: 50, tota...

StyleTTS 2 Setup Guide

HOWTO Guides

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models Samples: Paper: Repo: Style...

Comparing Quants

Logbook Future Project for different quants Perplexity https://oobabooga.github....