Create README.md

README.md

@@ -0,0 +1,38 @@
+
+## Creation
+
+```python
+from transformers import AutoProcessor, AutoModelForCausalLM
+
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.transformers import oneshot, wrap_hf_model_class
+
+MODEL_ID = "microsoft/Phi-3.5-vision-instruct"
+
+# Load model.
+model_class = wrap_hf_model_class(AutoModelForCausalLM)
+model = model_class.from_pretrained(MODEL_ID, device_map="auto", torch_dtype="auto", trust_remote_code=True, _attn_implementation="eager")
+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:model.vision_embed_tokens.*"],
+)
+
+# 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 ==============")
+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("==========================================")
+```