OPEA
/

DeepSeek-V3-int4-sym-gptq-inc

4-bit precision

Model card Files Files and versions Community

cicdatopea commited on 5 days ago

Commit

88165c5

·

verified ·

1 Parent(s): af0b9cd

the model has supported cuda

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -182,7 +182,7 @@ from auto_round import AutoRoundConfig ##must import for autoround format
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
-quantized_model_dir = "OPEA/DeepSeek-V3-int4-sym-inc-cpu"
 quantization_config = AutoRoundConfig(
     backend="cpu"
 )

 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+quantized_model_dir = "OPEA/DeepSeek-V3-int4-sym-gptq-inc"
 quantization_config = AutoRoundConfig(
     backend="cpu"
 )