Create README.md

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- fp8
+- vllm
+---
+
+# Qwen2-7B-Instruct-FP8
+
+## Model Overview
+Qwen2-7B-Instruct quantized to FP8 weights and activations using per-tensor quantization, ready for inference with vLLM >= 0.5.0.
+
+## Usage and Creation
+Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py).
+
+```python
+from datasets import load_dataset
+from transformers import AutoTokenizer
+
+from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
+
+pretrained_model_dir = "Qwen/Qwen2-7B-Instruct"
+quantized_model_dir = "Qwen2-7B-Instruct-FP8"
+
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True, model_max_length=4096)
+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)
+```
+
+## Evaluation
+
+### Open LLM Leaderboard evaluation scores
+|                      | Qwen2-7B-Instruct       | Qwen2-7B-Instruct-FP8<br>(this model) |
+| :------------------: | :----------------------: | :------------------------------------------------: |
+| arc-c<br>25-shot     | 62.37                    | 62.03                                              |
+| hellaswag<br>10-shot | 81.77                    | 81.46                                              |
+| mmlu<br>5-shot       | 70.82                    | 70.27                                              |
+| truthfulqa<br>0-shot | 57.36                    | 56.34                                              |
+| winogrande<br>5-shot | 76.16                    | 76.72                                              |
+| gsm8k<br>5-shot      | 68.84                    | 69.83                                              |
+| **Average<br>Accuracy**  | **69.55**                    |              **69.44**                                     |
+| **Recovery**             | **100%**                     |              **99.84%**                                     |
+