mpt-7b-ggml / mpt-7b-chat-q4_0.meta
LLukas22's picture
Upload new model file: 'mpt-7b-chat-q4_0.bin'
f28b702
raw
history blame
258 Bytes
{
"model": "Mpt",
"quantization": "Q4_0",
"quantization_version": "V2",
"container": "GGML",
"converter": "llm-rs",
"hash": "a0be978033bcd370a2c73b669669c1020534a63410fe03591095dcf1c53fb7dd",
"base_model": "mosaicml/mpt-7b-chat"
}