# Instruction Tuning

This is a quantized version of Gryphe's Codex-24B-Small-3.2 model, which optimizes the running efficiency under different hardware conditions through quantization technology.

Gemma 3 is a lightweight open model built by Google based on Gemini technology, supporting text and image inputs to generate text outputs. The 12B version is instruction-tuned and suitable for various generation and comprehension tasks.

Gemma 3 is a lightweight open-source large language model developed by Google. This repository provides its 4B parameter version with W4A16 quantization, significantly reducing hardware requirements.

Gemma 3 12B is a large language model that provides a quantized version in GGUF format, suitable for local deployment and use.

Gemma 3 is Google's lightweight cutting-edge open-source multimodal model supporting image-text input and text output, featuring a 128K context window and 140+ language support.

calme-3.2-instruct-78b is an advanced iterative version based on Qwen2.5-72B, a general-domain large language model with enhanced capabilities through self-merging and fine-tuning.

Mini Magnum is a streamlined version of magnum-72b-v1, aiming to replicate the text quality of the Claude 3 series (especially Sonnet and Opus). It is fine-tuned based on Mistral-Nemo-Base-2407, and a new general instruction dataset is added to improve coherence and alignment.

Llama 3.1 8B Instruct is a large language model released by Meta. It has been fixed and optimized for a specific version, improving performance and compatibility.

A large language model trained by ELYZA, based on Meta-Llama-3-8B-Instruct with enhanced Japanese capabilities

MMedLM is a multilingual language model focusing on the medical field. Based on the Llama 3 architecture, it performs excellently in tasks such as medical Q&A.

CodeGemma is a collection of lightweight open-source code models built on Gemma, supporting various tasks such as code completion, generation, and dialogue.

Meta-Llama-3-70B-Instruct is a 70B parameter-scale instruction-tuned large language model released by Meta, optimized for dialogue use cases, with outstanding performance in safety and helpfulness.

The GGUF format version of Llama 3 70B Instruct, providing a more efficient local running experience

OpenELM is a set of open-source efficient language models that employ a hierarchical scaling strategy to optimize parameter allocation, including pre-trained and instruction-tuned versions ranging from 270 million to 3 billion parameters.

OpenELM is a set of open-source efficient language models that adopt a hierarchical scaling strategy to efficiently allocate parameters in each layer of the Transformer model, improving accuracy.

CodeGemma is a lightweight open-source collection of code models based on Gemma, specializing in code generation, completion, and conversational tasks.

CodeGemma is a lightweight open-source code model series based on Gemma, focusing on code completion, generation, and conversational tasks.

Code Llama is a series of pre-trained generative text models released by Meta, focusing on code generation and understanding, with versions ranging from 7 billion to 34 billion parameters.

PiVoT-0.1-Evil-a is a Korean-English bilingual model fine-tuned based on Mistral 7B, providing GGUF files in various quantization formats suitable for different hardware environments.

An open-source large language model based on the Llama 2 series, enhanced for Japanese language capabilities, available in 7B/13B/70B sizes and instruction-tuned versions

A biomedical domain-specific model fine-tuned with instructions based on the Llama2 7B model

CodeLlama-13b-Instruct is a 13-billion-parameter instruction-tuned code generation model released by Meta, specifically designed for safe instruction following and code assistant applications

This is a GPT2 model fine-tuned on the open-instruct-v1 dataset, using the Alpaca-style prompt template for instruction tuning.