dolly-v2-ggml / dolly-v2-7b-q4_0-ggjt.meta
LLukas22's picture
Upload new model file: 'dolly-v2-7b-q4_0-ggjt.bin'
3b66d6b
raw
history blame
264 Bytes
{
"model": "GptNeoX",
"quantization": "Q4_0",
"quantization_version": "V2",
"container": "GGJT",
"converter": "llm-rs",
"hash": "16df8b6617709cda18ce8263e629e660d2ddc5413249b68fe07a0ca258d984cb",
"base_model": "databricks/dolly-v2-7b"
}