TroyDoesAI
/

Mermaid-Llama-3-5B-Pruned

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Mermaid-Llama-3-5B-Pruned / generation_config.json

TroyDoesAI's picture

How LOW can WE GO?! It still seems pretty coherent in my tests. here goes nothing.

914b793 verified 10 months ago

121 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": 128001,
	"transformers_version": "4.39.3"
	}