Create README.md

README.md

@@ -0,0 +1,124 @@
+---
+datasets:
+- NeelNanda/pile-10k
+base_model:
+- Qwen/QwQ-32B
+---
+## Model Details
+
+This model is an int4 model with group_size 128 and symmetric quantization of [Qwen/QwQ-32B](https://huggingface.co/Qwen/QwQ-32B) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm.
+
+## How To Use
+
+### INT4 Inference(CPU/HPU/CUDA)
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "OPEA/QwQ-32B-int4-AutoRound-gptq-sym"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "How many r's are in the word \"strawberry\""
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+##INT4:
+
+prompt = "9.11和9.8哪个数字大"
+
+
+
+prompt = "如果你是人，你最想做什么"
+
+
+prompt = "There are ten birds in a tree. A hunter shoots one. How many are left in the tree?"
+
+
+```
+
+
+
+### Evaluate the model
+
+pip3 install lm-eval==0.4.5
+
+```bash
+auto-round --model "OPEA/QwQ-32B-int4-AutoRound-gptq-sym" --eval --eval_bs 16  --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,openbookqa,boolq,arc_easy,arc_challenge,mmlu
+```
+
+
+
+| Metric         | BF16   | INT4   |
+| -------------- | ------ | ------ |
+| Avg            | 0.6600 | 0.6539 |
+| lambada_openai | 0.6697 | 0.6707 |
+| hellaswag      | 0.6520 | 0.6480 |
+| piqa           | 0.7947 | 0.8014 |
+| winorgrande    | 0.6977 | 0.6851 |
+| truthfulqa_mc1 | 0.4211 | 0.4125 |
+| openbookqa     | 0.3540 | 0.3360 |
+| boolq          | 0.8645 | 0.8483 |
+| arc_easy       | 0.8089 | 0.8068 |
+| arc_challenge  | 0.5392 | 0.5358 |
+| mmlu           | 0.7982 | 0.7943 |
+
+### Generate the model
+
+Here is the sample command to generate the model. For symmetric quantization, we found overflow/NAN will occur for some backends, so better fallback some layers. auto_round requires version >=0.4.1
+
+```bash
+auto-round \
+--model  Qwen/QwQ-32B \
+--device 0 \
+--group_size 128 \
+--bits 4 \
+--disable_eval \
+--format 'auto_gptq' \
+--output_dir "./tmp_autoround" 
+```
+
+
+
+## Ethical Considerations and Limitations
+
+The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
+
+Therefore, before deploying any applications of the model, developers should perform safety testing.
+
+## Caveats and Recommendations
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
+
+Here are a couple of useful links to learn more about Intel's AI software:
+
+- Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
+
+## Disclaimer
+
+The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
+
+## Cite