mpt-7b-ggml / mpt-7b-instruct-q5_1.meta
LLukas22's picture
Upload new model file: 'mpt-7b-instruct-q5_1.bin'
099e21e
raw
history blame contribute delete
262 Bytes
{
"model": "Mpt",
"quantization": "Q5_1",
"quantization_version": "V2",
"container": "GGML",
"converter": "llm-rs",
"hash": "856357829a979a8cf2198d9a787617bc83eb689b6d7efbc4350dca183364f895",
"base_model": "mosaicml/mpt-7b-instruct"
}