itroot
/

Qwen3-4B-Thinking-2507-W8A8

Text Generation

8-bit precision

Model card Files Files and versions

itroot commited on Sep 24

Commit

fc603d9

·

verified ·

1 Parent(s): 0060531

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -9,6 +9,7 @@ tags:
 - llm-compressor
 base_model:
 - Qwen/Qwen3-4B-Thinking-2507
 ---
 # Qwen3-4B-Thinking-2507 - W8A8 Quantized
@@ -91,4 +92,4 @@ SAVE_DIR = "Qwen3-4B-Thinking-2507-W8A8"
 print(f"Saving compressed model and tokenizer to '{SAVE_DIR}'...")
 model.save_pretrained(SAVE_DIR, save_compressed=True)
 tokenizer.save_pretrained(SAVE_DIR)
-```

 - llm-compressor
 base_model:
 - Qwen/Qwen3-4B-Thinking-2507
+pipeline_tag: text-generation
 ---
 # Qwen3-4B-Thinking-2507 - W8A8 Quantized
 print(f"Saving compressed model and tokenizer to '{SAVE_DIR}'...")
 model.save_pretrained(SAVE_DIR, save_compressed=True)
 tokenizer.save_pretrained(SAVE_DIR)
+```