Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.
Conventional Commits message generator in Brazilian Portuguese (PT-BR), fine-tuned from Qwen 2.5 Coder 7B. Receive a "git diff", return a single-line commit message in Conventional Commits format.
Unofficial OpenThaiGPT 1.5-7B-Instruct Q4_K_M Quantization (https://huggingface.co/openthaigpt/openthaigpt1.5-7b-instruct)
https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-64k-v0.1
A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.
Salamandra is a highly multilingual model pre-trained from scratch that comes in three different sizes — 2B, 7B, and 40B parameters — in base and instruction-tuned variants.
A new LLaVA model fine-tuned from Mistral's 7B model
pulled from https://huggingface.co/MaziyarPanahi/mamba-gpt-7b-v2-Mistral-7B-Instruct-v0.2-slerp-GGUF
This is a new kind of model optimization. This model is based on MaziyarPanahi/calme-2.1-qwen2-72b, which was tuned from Qwen2-72B.
Ternary CRACK · Abliterated · No guardrails · PQ2_0 ternary 2.13 bpw · 7.2 GB
5 Sovereign AI Models — Edge (1.5B), Reasoning (30B), Professional (22B), Verification (7B), Vision (8B). Unified ecosystem by NJIR.AI.
§ - Where Rules Come to Die 💀 No filters. No limits. No bullshit. Just raw, uncensored AI power. Access the forbidden knowledge. Break every rule. Watch the world burn. Your playground awaits, you beautiful bastard. 😈 🚫🤖🔥
This model is optimized for programming purposes. 7B parameters and based off codellama model.
A Quantize version of Biomistral made by MaziyarPanahi on HuggingFace. BioMistral-7B-GGUF Model creator: BioMistral Original model: BioMistral/BioMistral-7B
https://huggingface.co/MaziyarPanahi/BioMistral-7B-GGUF
Convert by https://huggingface.co/MetaStoneTec/MetaStone-L1-7B
quantization of yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
Derived from beowolx/MistralHermes-CodePro-7B-v1-GGUF and beowolx/MistralHermes-CodePro-7B-v1 for Q8_0
Unofficial THaLLE-0.1-7B-fa Q4_K_M Quantization (https://huggingface.co/KBTG-Labs/THaLLE-0.1-7B-fa)
This model is deptived by using SeaLLM 7B