cognitivecomputations
/

DeepSeek-R1-AWQ

Text Generation

4-bit precision

Model card Files Files and versions Community

DeepSeek-R1-AWQ / generation_config.json

v2ray's picture

Added README.md, prefill ability, and fixed cache.

8cb6f88 verified 2 days ago

137 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 0,
	"do_sample": true,
	"eos_token_id": 1,
	"transformers_version": "4.49.0.dev0"
	}