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.
LoftQ_-_Llama-2-13b-hf-4bit-64rank-ggufLoftQ_-_Mistral-7B-v0.1-4bit-32rank-ggufLoftQ_-_Llama-2-7b-hf-2bit-32rank-ggufLMIM.Genesys-e_w-soul-Lofty-0.8BLoftQ_-_Llama-2-7b-hf-2bit-64rank-ggufHo97_-_llama2_7b_loftq_w2a16_r64-ggufLoftQ_-_phi-2-4bit-64rank-ggufMeta-Llama-3-8B-4bit-64rankloftrCaden-SQL-1.5B-GGUFminima-loftrstarcoder-3b-hugcoder-loftq-mergedphi-2-4bit-64rankCodeLlama-70b-hf-4bit-64rankMeta-Llama-3-70B-Instruct-4bit-64rankPhi-3-mini-128k-instruct-4bit-64rankLlama-2-7b-hf-4bit-64rankMeta-Llama-3-70B-4bit-64rank-1iterMeta-Llama-3-8B-Instruct-4bit-64rankLlama-2-70b-hf-4bit-64rankCodeLlama-7b-hf-4bit-64rankMeta-Llama-3-70B-4bit-64rankTinyLlama-1.1B-4bit-32rank-loftq-adaptersloftup-dinov2sbart-large-bit2-rank8Llama-2-13b-hf-4bit-64rankLeoLM-leo-mistral-7b-mixtral-and-gpt4-explanation-3-epochs-loftq-finetunedMistral-7B-v0.1-oasstguanaco-1e-loftq-mergedCodeLlama-13b-hf-4bit-64rankPhi-3-mini-4k-instruct-4bit-64rank