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.
jais-family-6p7b-chat_bitsandbytes_4bitjais-13b-chat_bitsandbytes_8bitjais-13b-chat_bitsandbytes_4bitjais-family-6p7b-chat_bitsandbytes_8bitOLD_bitsandbytes4bit_16acphi2_qlora_emailGen_bitsandbytesjais-family-590m-chat_bitsandbytes_4bitjais-family-590m-chat_bitsandbytes_8bitjais-family-590m-chat_bitsandbytes_4bitmistral-fc-10ep-bitsandbytesjais-family-590m-chat_bitsandbytes_8bitLlama-2-7b-chat-hf-bitsandbytes-8bitPRELIM_MNLP_M3_quantized_model_lr5eminus5_bitsandbytes4bit_16acMeta-Llama-3-8B-Instruct_bitsandbytes_4bitMistral-7B-Instruct-v0.2-quantized-bitsandbytesnano-mistral_bitsandbytes_int8PRELIM_MNLP_M3_quantized_model_lr5eminus5_bitsandbytes4bit_16ac_nestedkanana-safeguard-8b-bitsandbytes-4bitLlama-2-7b-chat-hf-bitsandbytesMeta-Llama-3-70B-Instruct-BitsAndBytesLlama-3.1-8B_bitsandbytes_int4_d_nf4opt-350m-BitsAndBytes-4bitPRELIM_MNLP_M3_quantized_model_lr5eminus5_bitsandbytes8bit_16acLlama-3.1-8B_bitsandbytes_int4_dMeta-Llama-3-8B-Instruct-bitsandbytesOLD_bitsandbytes4bit_16ac_nestedMNLP_M3_quantized_model_bitsandbytes4bit_16ac_nestednano-mistral_bitsandbytes_int4opt-350m-BitsAndBytes-8bitcompressed_model_BitsAndBytesConfig_4bit