20+ models
For testing purposes only. From https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-i1-GGUF/blob/main/README.md.
MediaTek Research Breeze-7B (hereinafter referred to as Breeze-7B) is a language model family that builds on top of Mistral-7B, specifically intended for Traditional Chinese use. 〈F16 / Q4〉
Converted to Q8_0 from https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0
Breeze-7B-32k-Instruct derives from the base model Breeze-7B-32k-Base, making the resulting model amenable to be used as-is for commonly seen tasks. 〈f16, Q4, Q4_K_M〉
https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-64k-v0.1
Use `https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-text-only-i1-GGUF/blob/main/Llama-Breeze2-8B-Instruct-text-only.i1-Q4_K_M.gguf` and disable default template. Please run it with the code in `https://github.com/mtkresearch/mtkresearch`.
Breeze-7B is a language model family that builds on top of Mistral-7B, specifically intended for Traditional Chinese use.
MediaTek-Research/Breeze-7B-Instruct-v0.1 from MediaTech Research
BeansLLM 2 mid training release with zero finetuning, loss 2.9
This is an essay writing model extremely effective at evading the ZeroGPT classifier. Performance is not guaranteed on other AI detection tools. This model is for research only, please do not use it for malicious purposes or to cheat on your homework.
Decensored Qwen2.5-Coder-3B-Instruct with 3/100 refusals and near-zero KL divergence via Heretic abliteration.