Create README.md

README.md

@@ -0,0 +1,45 @@
+
+## Evaluation
+
+```
+TBD
+```
+
+## Creation
+https://github.com/vllm-project/llm-compressor/pull/185
+
+```python
+from transformers import AutoProcessor
+
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.transformers import oneshot
+from llmcompressor.transformers.sparsification import create_sparse_auto_model_class
+
+MODEL_ID = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+
+# Load model.
+model_class = create_sparse_auto_model_class("MllamaForConditionalGeneration")
+model = model_class.from_pretrained(MODEL_ID, device_map="auto", torch_dtype="auto")
+processor = AutoProcessor.from_pretrained(MODEL_ID)
+
+# Configure the quantization algorithm and scheme.
+# In this case, we:
+#   * 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=["re:.*lm_head", "re:multi_modal_projector.*", "re:vision_model.*"],
+)
+
+# 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)
+
+# Confirm generations of the quantized model look sane.
+print("========== SAMPLE GENERATION ==============")
+input_ids = processor(text="Hello my name is", return_tensors="pt").input_ids.to("cuda")
+output = model.generate(input_ids, max_new_tokens=20)
+print(processor.decode(output[0]))
+print("==========================================")
+```