# Lightweight conversational model

A quantized version based on the katanemo/Arch-Function-Chat-3B model, quantized using llama.cpp, supporting multiple quantization types, suitable for text generation tasks.

Phi-3 Mini-4K-Instruct ONNX model for in-browser inference, accelerated via ONNX Runtime Web for browser-based processing.

MiniLLM is a lightweight language model project that fully implements the entire process from pre-training → instruction fine-tuning → reward modeling → reinforcement learning, economically and efficiently building a chat model with basic conversational capabilities

Minueza-32M-UltraChat is a 32-million-parameter conversational model, trained on Minueza-32M-Base, focusing on text generation tasks.

A 31-million parameter conversational model fine-tuned from EleutherAI/pythia-31m, supporting multi-turn dialogues and various task scenarios

TinyLlama is a lightweight 1.1B-parameter Llama model pre-trained on 3 trillion tokens, fine-tuned for conversation and alignment optimized, suitable for resource-constrained scenarios.

MobileLLaMA-1.4B-Chat is a chat model fine-tuned from MobileLLaMA-1.4B-Base, utilizing the ShareGPT dataset for supervised instruction fine-tuning.

A dialogue model developed based on LLaMA 3B v2, supporting text generation tasks, with moderate performance on the open large model leaderboard.

This is a 160M-parameter Llama chat model, fine-tuned from JackFram/llama-160m, focusing on text generation tasks.

TinyLlama-1.1B-Chat-v0.6 is a lightweight chat model based on the 1.1B-parameter Llama architecture, optimized for conversational tasks.

TinyMistral-248M-Chat is a chat model fine-tuned based on TinyMistral-248M, supporting multi-turn conversations and suitable for various dialogue scenarios.

TinyMistral-248M-Chat is a chat model based on TinyMistral-248M, trained and optimized on multiple datasets, suitable for various conversational tasks.

TinyLlama-1.1B is a compact large language model with 1.1 billion parameters, based on the Llama 2 architecture, optimized for computation and memory-constrained scenarios.

TinyLlama-1.1B is a lightweight language model based on the Llama 2 architecture with 1.1B parameters, designed for computation and memory-constrained applications.

A lightweight conversational model fine-tuned based on TinyLlama-1.1B, trained using the Alpaca dataset, suitable for English text generation tasks

TinyLlama is a compact 1.1B-parameter language model pre-trained on 3 trillion tokens, suitable for applications with limited computational resources.