Siddharth63
/

Qwen3-8B-Base-4bits-AutoRound-asym

4-bit precision

Model card Files Files and versions

Siddharth63 commited on May 2, 2025

Commit

6e61ef9

·

verified ·

1 Parent(s): a99f90b

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -8,7 +8,7 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 from auto_round import AutoRoundConfig  ## must import for auto-round format
-quantized_model_path = "Siddharth63/Qwen3-4B-Base-4bit-Autoround-asym"
 quantization_config = AutoRoundConfig(backend="auto")
 model = AutoModelForCausalLM.from_pretrained(quantized_model_path, device_map="auto",
                                              torch_dtype=torch.float16,

 import torch
 from auto_round import AutoRoundConfig  ## must import for auto-round format
+quantized_model_path = "Siddharth63/Qwen3-8B-Base-4bit-Autoround-asym"
 quantization_config = AutoRoundConfig(backend="auto")
 model = AutoModelForCausalLM.from_pretrained(quantized_model_path, device_map="auto",
                                              torch_dtype=torch.float16,