Update README.md

README.md

@@ -1,4 +1,35 @@
 ---
 base_model:
 - openbmb/MiniCPM-V-2_6
----
+---
+
+## Creation
+
+```python
+from transformers import AutoProcessor, AutoModelForCausalLM
+
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.transformers import oneshot, wrap_hf_model_class
+
+MODEL_ID = "openbmb/MiniCPM-V-2_6"
+
+# Load model.
+model_class = wrap_hf_model_class(AutoModelForCausalLM)
+model = model_class.from_pretrained(MODEL_ID, torch_dtype="auto", trust_remote_code=True).to("cuda")
+processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
+
+# 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:resampler.*", "re:vpm.*"],
+)
+
+# 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, trust_remote_code_model=True)
+processor.save_pretrained(SAVE_DIR)
+```