mpt-7b-ggml / mpt-7b-instruct-q4_0-ggjt.meta
LLukas22's picture
Upload new model file: 'mpt-7b-instruct-q4_0-ggjt.bin'
64f8561
raw
history blame
262 Bytes
{
"model": "Mpt",
"quantization": "Q4_0",
"quantization_version": "V2",
"container": "GGJT",
"converter": "llm-rs",
"hash": "216adda03f2c20fdeefa2599571327deec2fa544b49aee57c1672b840180dcc5",
"base_model": "mosaicml/mpt-7b-instruct"
}