pythia-ggml / pythia-410m-f16.meta
LLukas22's picture
Upload new model file: 'pythia-410m-f16.bin'
b578ea7
raw
history blame
274 Bytes
{
"model": "GptNeoX",
"quantization": "F16",
"quantization_version": "Not_Quantized",
"container": "GGML",
"converter": "llm-rs",
"hash": "c11f242900f8545316b2a25700c0a15f3a2a677d6fa495906e978f598a1c5b36",
"base_model": "EleutherAI/pythia-410m"
}