Add code snippet and other sections

README.md

@@ -16,19 +16,58 @@ tags:
 This model was converted to GGUF format from [`BitStarWalkin/SuperCorrect-7B`](https://huggingface.co/BitStarWalkin/SuperCorrect-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
 Refer to the [original model card](https://huggingface.co/BitStarWalkin/SuperCorrect-7B) for more details on the model.
 
----
-
 ## Model Description
 SuperCorrect is a novel two-stage fine-tuning method for improving both reasoning accuracy and self-correction ability for LLMs. It incorporates LLMs with a pre-defined hierarchical thought template (Buffer of Thought (BoT)) to conduct more deliberate reasoning. Notably, SuperCorrect-7B significantly surpasses powerful DeepSeekMath-7B by 7.8%/5.3% and Qwen2.5-Math-7B by 15.1%/6.3% on MATH/GSM8K benchmarks, achieving new SOTA performance among all 7B models. It relies on pure mathematical reasoning abilities of LLMs, instead of leveraging other programming methods such as PoT and ToRA.
 
 ## Paper
 
-[SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights](https://hf.co/papers/2410.09008)
+[SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights](https://huggingface.co/papers/2410.09008)
 
 ## Code
 
 https://github.com/YangLing0818/SuperCorrect-llm
 
+## Use with Transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "BitStarWalkin/SuperCorrect-7B"
+device = "cuda" 
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Find the distance between the foci of the ellipse \[9x^2 + \frac{y^2}{9} = 99.\]"
+hierarchical_prompt = "Solve the following math problem in a step-by-step XML format, each step should be enclosed within tags like <Step1></Step1>. For each step enclosed within the tags, determine if this step is challenging and tricky, if so, add detailed explanation and analysis enclosed within <Key> </Key> in this step, as helpful annotations to help you thinking and remind yourself how to conduct reasoning correctly. After all the reasoning steps, summarize the common solution and reasoning steps to help you and your classmates who are not good at math generalize to similar problems within <Generalized></Generalized>. Finally present the final answer within <Answer> </Answer>."
+# HT
+messages = [
+    {"role": "system", "content":hierarchical_prompt },
+    {"role": "user", "content": prompt}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=1024
+)
+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)
+```
 
 ## Use with llama.cpp
 Install llama.cpp through brew (works on Mac and Linux)
@@ -68,4 +107,29 @@ Step 3: Run inference through the main binary.
 or 
 ```
 ./llama-server --hf-repo Triangle104/SuperCorrect-7B-Q6_K-GGUF --hf-file supercorrect-7b-q6_k.gguf -c 2048
+```
+
+## Acknowledgements
+
+Our SuperCorrect is a two-stage fine-tuning model which based on several extraordinary open-source models like Qwen2.5-Math, DeepSeek-Math, Llama3-Series. Our evaluation method is based on the code base of outstanding works like Qwen2.5-Math and lm-evaluation-harness. We also want to express our gratitude for amazing works such as BoT which provides the idea of thought template.
+
+## Performance
+
+We evaluate our SupperCorrect-7B on two widely used English math benchmarks GSM8K and MATH. All evaluations are tested with our evaluation method which is zero-shot hierarchical thought based prompting.
+
+## Citation
+
+```bibtex
+@article{yang2024supercorrect,
+title={SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights}
+  author={Yang, Ling and Yu, Zhaochen and Zhang, Tianjun and Xu, Minkai and Gonzalez, Joseph E and Cui, Bin and Yan, Shuicheng},
+  journal={arXiv preprint arXiv:2410.09008},
+  year={2024}
+}
+@article{yang2024buffer,
+  title={Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models},
+  author={Yang, Ling and Yu, Zhaochen and Zhang, Tianjun and Cao, Shiyi and Xu, Minkai and Zhang, Wentao and Gonzalez, Joseph E and Cui, Bin},
+  journal={arXiv preprint arXiv:2406.04271},
+  year={2024}
+}
 ```