richie-ghost
/

llama-3b-unsloth-quantized_merged_8bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

llama-3b-unsloth-quantized_merged_8bit / generation_config.json

richie-ghost's picture

Trained with Unsloth

a3320e8 verified 5 months ago

history blame contribute delete

No virus

143 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": [
	128001,
	128009
	],
	"transformers_version": "4.40.0"
	}