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.
madlad400-3b-mt-bitsandbytes-4bitm2m100_418-mt-bitsandbytes-4bitjais-family-6p7b-chat_bitsandbytes_4bitjais-family-590m-chat_bitsandbytes_8bitmistral-fc-10ep-bitsandbytesjais-family-6p7b-chat_bitsandbytes_8bitjais-family-590m-chat_bitsandbytes_8bitjais-family-590m-chat_bitsandbytes_4bitjais-family-590m-chat_bitsandbytes_4bitphi2_qlora_emailGen_bitsandbytesMistral-7B-Instruct-v0.2-quantized-bitsandbytesMeta-Llama-3-70B-Instruct-BitsAndBytesLlama-2-7b-chat-hf-bitsandbytesopt-350m-BitsAndBytes-8bitnllb-200-distilled-600M-bitsandbytes-4bit-cpuLlama-3.1-8B_bitsandbytes_int4_d_nf4_prunedLlama-3.1-8B_bitsandbytes_int4_d_nf4nllb-200-distilled-1.3B-bitsandbytes-4bit-cpuMeta-Llama-3-8B-Instruct_bitsandbytes_4bitnano-mistral_bitsandbytes_int8nano-mistral_bitsandbytes_int4Llama-2-13b-chat-hf-bitsandbytes-8bitopt-350m-BitsAndBytes-4bitLlama-3.1-8B_bitsandbytes_int4_dMeta-Llama-3-8B-Instruct-bitsandbytescompressed_model_BitsAndBytesConfig_4bitPRELIM_MNLP_M3_quantized_model_lr5eminus5_bitsandbytes8bit_16acPRELIM_MNLP_M3_quantized_model_lr5eminus5_bitsandbytes4bit_16ac_nestedMNLP_M3_quantized_model_bitsandbytes4bit_16ac_nestedMeta-Llama-3-8B-Instruct-bitsandbytes-8bit