Update README.md

README.md

@@ -2,4 +2,30 @@
 license: apache-2.0
 base_model:
 - rhymes-ai/Aria-sequential_mlp
----
+---
+# Aria-sequential_mlp-FP8-dynamic
+
+FP8-Dynamic quant from rhymes-ai Aria made with llm-compressor.
+
+Generated with the following code:
+
+```
+from transformers import AutoProcessor, AutoModelForCausalLM
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
+
+model_name = "rhymes-ai/Aria-sequential_mlp"
+
+model = SparseAutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True)
+processor = AutoProcessor.from_pretrained(model_name, trust_remote_code=True)
+
+recipe = QuantizationModifier(
+    targets="Linear",
+    scheme="FP8_DYNAMIC",
+    ignore=["re:.*lm_head", "re:multi_modal_projector.*", "re:vision_tower.*"],
+)
+
+folder = model_name.split("/")[1] + "-FP8-Dynamic"
+oneshot(model=model, recipe=recipe, output_dir=folder)
+processor.save_pretrained(folder)
+```