mpt-7b-ggml / mpt-7b-instruct-q5_1-ggjt.meta
LLukas22's picture
Upload new model file: 'mpt-7b-instruct-q5_1-ggjt.bin'
e0b03d5
raw
history blame
262 Bytes
{
"model": "Mpt",
"quantization": "Q5_1",
"quantization_version": "V2",
"container": "GGJT",
"converter": "llm-rs",
"hash": "2331ea1208288cd52bcaaae555f231f9a51a264f4b8548a7998da43573e6935a",
"base_model": "mosaicml/mpt-7b-instruct"
}