models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
LLaMA3.1-8B-Instruct-DFlash-UltraChatLLaMAntino-2-chat-13b-hf-UltraChat-ITALlama-3-8B-4bit-UltraChat-ItaQwen2.5-1.5B-ultrachat200kphi-2-sft-ultrachat-fullLLaMAntino-2-70b-hf-UltraChat-ITAQwen2.5-14B-Instruct_EAGLE3_UltraChatLlama-3-8B-Ultrachat-200K-GGUFzephyr-7b-gemma-sft-african-ultrachat-200k-GGUFQwen2.5-7B-Instruct_EAGLE3_UltraChatdistil-zephyr-1.5b-ssft-ultrachatneuralmagic-Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUFAfrican-ultrachat-alpaca-GGUFMinueza-32M-UltraChatneuralmagic.Sparse-Llama-3.1-8B-ultrachat_200k-2of4-GGUFQwen2.5-32B-Instruct_EAGLE3_UltraChatQwen2.5-7B-sft-ultrachat-SPIN-gpt4o-GGUFgemma-7b-ultrachat-sftgpt2-ultrachat-finetunedSparseLLama-2-7b-ultrachat_200k-pruned_50.2of4Llama-2-7b-ultrachat200k-GGUFQwen3-1.7B-UltraChat-SFTLlama-2-7b-ultrachat200kSparse-Llama-3.1-8B-ultrachat_200k-2of4LLaMA3.1-8B-Instruct-DFlash-UltraChat-RTN-INT8-Safetensorsllama-3-8b-base-sft-ultrachat-8xh200mistral-7b-sft-ultrachat-arithmo-fullLlama-2-7b-ultrachat200k-pruned_70Sparse-Llama-3.1-8B-ultrachat_200k-2of4-quantized.w4a16mamba-2.8b-ultrachat-hf