pythia-ggml / pythia-160m-f16.meta
LLukas22's picture
Upload new model file: 'pythia-160m-f16.bin'
ca08a49
raw
history blame
230 Bytes
{
"model": "GptNeoX",
"quantization": "F16",
"quantization_version": "Not_Quantized",
"container": "GGML",
"converter": "llm-rs",
"hash": "cd3b0567e4ceee6f4e7c44147f1e4332dc92c6867f1397ab3bf21159716a9c6b"
}