GIPmbH
/

Mistral-7B-Instruct-v0.2-quantized

Text Generation

Inference Endpoints

text-generation-inference

4-bit precision

🇪🇺 Region: EU

Model card Files Files and versions Community

Mistral-7B-Instruct-v0.2-quantized / generation_config.json

MatthiasAppelGip's picture

MatthiasAppelGip

Upload MistralForCausalLM

6be6043 verified 3 months ago

raw history blame contribute delete

No virus

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.39.3"
	}