xavierbarbier
/

mistral-7b-instruct-v0.1-hf-quant

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions Community

mistral-7b-instruct-v0.1-hf-quant / generation_config.json

xavierbarbier's picture

Upload MistralForCausalLM

5f08eda over 1 year ago

history blame contribute delete

111 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.36.0"
	}