pytorch
/

Qwen3-8B-int4wo-hqq

Text Generation

text-generation-inference

Model card Files Files and versions Community

jerryzh168 commited on 5 days ago

Commit

11d1522

·

verified ·

1 Parent(s): 37df94d

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -124,7 +124,7 @@ Use the following code to get the quantized model:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig
-model_id = "microsoft/Phi-4-mini-instruct"
 from torchao.quantization import Int4WeightOnlyConfig
 quant_config = Int4WeightOnlyConfig(group_size=128, use_hqq=True)

 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TorchAoConfig
+model_id = "Qwen/Qwen3-8B"
 from torchao.quantization import Int4WeightOnlyConfig
 quant_config = Int4WeightOnlyConfig(group_size=128, use_hqq=True)