Create README.md

README.md

@@ -0,0 +1,33 @@
+---
+tags:
+- fp8
+---
+
+# Qwen2-72B-Instruct-FP8 
+
+Quantized with [AutoFP8](https://github.com/neuralmagic/autofp8) using the following script on 8xA100:
+
+```python
+from datasets import load_dataset
+from transformers import AutoTokenizer
+
+from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
+
+pretrained_model_dir = "Qwen/Qwen2-72B-Instruct"
+quantized_model_dir = "Qwen2-72B-Instruct-FP8"
+
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True)
+tokenizer.pad_token = tokenizer.eos_token
+
+ds = load_dataset("mgoin/ultrachat_2k", split="train_sft").select(range(512))
+examples = [tokenizer.apply_chat_template(batch["messages"], tokenize=False) for batch in ds]
+examples = tokenizer(examples, padding=True, truncation=True, return_tensors="pt").to("cuda")
+
+quantize_config = BaseQuantizeConfig(quant_method="fp8", activation_scheme="static")
+
+model = AutoFP8ForCausalLM.from_pretrained(
+    pretrained_model_dir, quantize_config=quantize_config
+)
+model.quantize(examples)
+model.save_quantized(quantized_model_dir)
+```