AAProject
/

deepseek-math-7b-rl-8bits-Q

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

deepseek-math-7b-rl-8bits-Q / generation_config.json

AAProject's picture

Upload LlamaForCausalLM

7c46797 verified 5 months ago

history blame contribute delete

No virus

126 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 100000,
	"eos_token_id": 100001,
	"transformers_version": "4.42.0.dev0"
	}