K-Compression/HyperCLOVAX-SEED-Think-14B-GPTQ

This repo contains GPTQ model files for HyperCLOVAX-SEED-Think-14B. HyperCLOVAX-SEED-Think-14B-GPTQ was quantized using gptqmodel v4.0.0, following the guide. - Original model: [naver-hyperclovax/HyperCLOVAX-SEED-Think-14B](https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-14B/blob/main/config.json) - Quantization: GPTQ with 4-bit group-wise weight-only quantization (W4A16g128) from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "K-Compression/HyperCLOVAX-SEED-Think-14B-GPTQ" model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="bfloat16", device_map="auto" ) tokenizer = AutoTokenizer.from_pretrained(model_name) The model is licensed under [HyperCLOVA X SEED Model License Agreement](https://huggingface.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-14B/blob/main/LICENSE)