jwnder
/

codellama_CodeLlama-70b-Instruct-hf-bnb-4bit

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

Model card Files Files and versions Community

codellama_CodeLlama-70b-Instruct-hf-bnb-4bit / added_tokens.json

jwnder's picture

Upload tokenizer

46be3ed verified 3 months ago

raw history blame contribute delete

No virus

22 Bytes

	{
	"<step>": 32015
	}