Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

fixed typo

wenhuach21742cc27a2da2
diff --git a/README.md b/README.md
index a3b996182..28c8f91a5 100644
--- a/README.md
+++ b/README.md
@@ -39,7 +39,7 @@ prompt = "Once upon a time, a little girl"
tokenizer = AutoTokenizer.from_pretrained(output_dir, trust_remote_code=True)
inputs = tokenizer(prompt, return_tensors="pt").input_ids
streamer = TextStreamer(tokenizer)
-model = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=woq_config, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(output_dir, quantization_config=woq_config, trust_remote_code=True)
outputs = model.generate(inputs, streamer=streamer, max_new_tokens=300)