Update README.md

README.md

@@ -1,16 +1,20 @@
-https://github.com/vllm-project/llm-compressor/pull/185
+---
+base_model:
+- Qwen/Qwen2-VL-7B-Instruct
+---
+
+## Creation
 
 ```python
-from transformers import AutoProcessor
+from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
 
 from llmcompressor.modifiers.quantization import QuantizationModifier
-from llmcompressor.transformers import oneshot
-from llmcompressor.transformers.sparsification import create_sparse_auto_model_class
+from llmcompressor.transformers import oneshot, wrap_hf_model_class
 
 MODEL_ID = "Qwen/Qwen2-VL-7B-Instruct"
 
 # Load model.
-model_class = create_sparse_auto_model_class("Qwen2VLForConditionalGeneration")
+model_class = wrap_hf_model_class(Qwen2VLForConditionalGeneration)
 model = model_class.from_pretrained(MODEL_ID, device_map="auto", torch_dtype="auto")
 processor = AutoProcessor.from_pretrained(MODEL_ID)
 
@@ -19,11 +23,15 @@ processor = AutoProcessor.from_pretrained(MODEL_ID)
 #   * quantize the weights to fp8 with per channel via ptq
 #   * quantize the activations to fp8 with dynamic per token
 recipe = QuantizationModifier(
-    targets="Linear", scheme="FP8_DYNAMIC", ignore=["lm_head"]
+    targets="Linear",
+    scheme="FP8_DYNAMIC",
+    ignore=["re:.*lm_head", "re:visual.*"],
 )
 
-# Apply quantization.
-oneshot(model=model, recipe=recipe)
+# Apply quantization and save to disk in compressed-tensors format.
+SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-dynamic"
+oneshot(model=model, recipe=recipe, output_dir=SAVE_DIR)
+processor.save_pretrained(SAVE_DIR)
 
 # Confirm generations of the quantized model look sane.
 print("========== SAMPLE GENERATION ==============")
@@ -31,9 +39,4 @@ input_ids = processor(text="Hello my name is", return_tensors="pt").input_ids.to
 output = model.generate(input_ids, max_new_tokens=20)
 print(processor.decode(output[0]))
 print("==========================================")
-
-# Save to disk in compressed-tensors format.
-SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-Dynamic"
-model.save_pretrained(SAVE_DIR)
-processor.save_pretrained(SAVE_DIR)
 ```