AI Agent Hub

LLM Models

Browse the world's large language models. Compare parameters, benchmarks, VRAM and more.

1,294 models for "Transformer" Compare
🤖
opencole-typographylmm-llava-v1.5-7b-lora
cyberagent

This model is based on LLaVA1.5-7b. The model is finetuned with LoRA on OpenCOLE1.0 dataset to generate text layouts.

Open Source 7.0B ↓ 16
🤖
Qwen2.5-0.5B-DuDi
aisingapore

This model is a fine-tuned version of Qwen2.5-0.5B. It has been trained using TRL.

Open Source 0.5B ↓ 15
🤖
youri-7b-instruction-gptq
rinna

Overview rinna/youri-7b-instruction-gptq is the quantized model for rinna/youri-7b-instruction using AutoGPTQ. The quantized version is 4x smaller than the original model and thus requires less memory and provides faster inference.

Open Source 7.0B ↓ 12
🤖
youri-7b-gptq
rinna

Overview rinna/youri-7b-gptq is the quantized model for rinna/youri-7b using AutoGPTQ. The quantized version is 4x smaller than the original model and thus requires less memory and provides faster inference.

Open Source 7.0B ↓ 12
🤖
youri-7b-chat-gptq
rinna

Overview rinna/youri-7b-chat-gptq is the quantized model for rinna/youri-7b-chat using AutoGPTQ. The quantized version is 4x smaller than the original model and thus requires less memory and provides faster inference.

Open Source 7.0B ↓ 12
🤖
Qwen3-0.6B-Base-DuDi
aisingapore

This model is a fine-tuned version of Qwen3-0.6B-Base. It has been trained using TRL.

Open Source 0.6B ↓ 10
🤖
Llama3.2-1B-DuDi
aisingapore

This model is a fine-tuned version of Llama-3.2-1B. It has been trained using TRL.

Open Source 1.0B ↓ 9
🤖
Qwen2.5-1.5B-DuDi
aisingapore

This model is a fine-tuned version of Qwen2.5-1.5B. It has been trained using TRL.

Open Source 1.5B ↓ 8
🤖
bilingual-gpt-neox-4b-minigpt4
rinna

Overview This repository provides an English-Japanese bilingual multimodal conversational model like MiniGPT-4 by combining GPT-NeoX model of 3.8 billion parameters and BLIP-2.

Open Source 4.0B
🤖
starcoderplus-megatron
bigcode

Play with the instruction-tuned StarCoderPlus at StarChat-Beta.

Code