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.
Sparse-Llama-3.1-8B-2of4-GGUFneuralmagic_-_SparseLlama-3-8B-pruned_50.2of4-ggufSparse-Llama-3.1-8B-2of4-GGUFSparseLlama-3-8B-pruned_50.2of4-GGUFneuralmagic-SparseLlama-3-8B-pruned_50.2of4-GGUFSparse-Llama-3.1-8B-2of4Sparse-Llama-3.1-8B-2of4-GGUFSparseLlama-3-8B-pruned_50.2of4Sparse_llama-7BSparseLLama-2-7b-ultrachat_200k-pruned_50.2of4Sparse-Llama-3.1-8B-ultrachat_200k-2of4SparseLlama-3.1-8B-gsm8k-pruned.2of4-chnl_wts_per_tok_dyn_act_fp8-BitMSparse-Llama-3.1-8B-ultrachat_200k-2of4-quantized.w4a16Sparse-Llama-3.1-8B-gsm8k-2of4-FP8-dynamicSparseLlama-2-7b-evolcodealpaca-pruned_50.2of4Sparse-Llama-3.1-8B-gsm8k-2of4-quantized.w4a16SparseLlama-2-7b-cnn-daily-mail-pruned_50.2of4Sparse-Llama-3.1-8B-gsm8k-2of4Sparse-Llama-3.1-8B-evolcodealpaca-2of4sparse_llama_7b_refined_web_50p_2024-03-24sparse_llama_7b_refined_web_90p_2024-03-22sparse_llama_7b_hf2_refined_web_90p_2024-03-28Sparse-Llama-3.1-8B-evolcodealpaca-2of4-FP8-dynamicSparse-Llama-3.1-8B-evolcodealpaca-2of4-quantized.w4a16Sparse-Llama-3.1-8B-tldr-2of4-FP8-dynamicsparse_llama_7b_hf2_refined_web_50p_2024-05-12Sparse-Llama-3.1-8B-ultrachat_200k-2of4-FP8-dynamicsparse_llama_7b_hf2_refined_web_50p_2024-03-27sparse_llama_7b_hf2_refined_web_70p_2024-03-28sparse_llama_7b_refined_web_90p_debugging_2024-03-21