# Open Source for Commercial Use

A collection of GGUF quantized versions of MagTie-v1-12B, created by merging pre-trained language models using mergekit, suitable for text generation tasks.

This is the GGUF quantized version of the Josiefied-Qwen3-4B-abliterated-v1 model, suitable for local deployment and execution.

OLMo 2 1B is the smallest model in the open language model series released by the Allen Institute for Artificial Intelligence, based on OLMo-mix-1124 pre-training and further trained with the Dolmino-mix-1124 dataset during the intermediate training phase.

This model is a GGUF format model converted from the IBM Granite-3.3-8B instruction fine-tuned model, suitable for text generation tasks.

This is a transformers model hosted on Hugging Face Hub. Specific functionalities and use cases require further information.

Qwen2-VL-7B-Instruct is a 7B-parameter multimodal model supporting image-text interaction tasks.

LibreFLUX is the Apache 2.0 open-source version of FLUX.1-schnell, restoring full T5 context length and classifier-free guidance, removing aesthetic fine-tuning content, making it more suitable for secondary development

Yi-VL-6B is a multimodal vision-language model developed by 01-AI, supporting both Chinese and English, suitable for tasks like visual question answering.

Bllossom is a Korean-English bilingual language model based on Llama3, enhanced through comprehensive tuning to improve Korean language capabilities, expanding Korean vocabulary and optimizing Korean context processing.

A lightweight visual question answering model based on TinyLlama-1.1B, trained using the BakLlava codebase

Chinese-LLaMA-2-1.3B is a Chinese foundational model based on Meta's released Llama-2 model, expanded with a Chinese vocabulary and pre-trained in Chinese to enhance basic semantic understanding capabilities in Chinese.

The first publicly available commercial German foundation language model based on Mistral 7b, extending Llama-2's German capabilities through large-scale German corpus continual pre-training.

Mistral-7B-Instruct-v0.1 is a version of the Mistral-7B-v0.1 generative text model fine-tuned with various public dialogue datasets for instruction following.

Llama 2 is an open-source large language model series developed by Meta. The 13B version is a medium-scale model suitable for various text generation tasks.

Meta's 13B parameter chat model from the Llama 2 series, using GGUF quantization format, suitable for dialogue scenarios

An open-source and commercially usable bilingual (Chinese-English) vision-language assistant supporting multimodal dialogue in both languages

LLaVA-Lightning-7B is a multimodal model based on LLaMA-7B, achieving efficient vision-language task processing through delta parameter tuning.

A 6.9-billion-parameter instruction-tuned large language model released by Databricks, based on Pythia-6.9b architecture, permitted for commercial use

A 12-billion-parameter instruction fine-tuned large language model launched by Databricks, fine-tuned on 15K instruction data points based on pythia-12b, with commercial use permitted