Update README.md

README.md

@@ -1,35 +1,90 @@
 ---
-base_model: AI-MO/deepseek-math-7b-sft
+base_model: deepseek-ai/deepseek-math-7b-base
 tags:
 - alignment-handbook
 - generated_from_trainer
 datasets:
 - AI-MO/tora-chosen-v0.7
+widget:
+  - example_title: Math problem
+    messages:
+      - role: user
+        content: "For how many values of the constant $k$ will the polynomial $x^{2}+kx+36$ have two distinct integer roots?"
+    output:
+      text: >-
+        ### Solution: 1. For the polynomial \\( x^2 + kx + 36 \\) to have two distinct integer roots, let's denote these roots by \\( r_1 \\) and \\( r_2 \\).\n\n2. According to Vieta's formulas, the sum of the roots \\( r_1 + r_2 \\) is equal to \\(-k\\), and the product of the roots \\( r_1 \\cdot r_2 \\) is equal to 36.\n\n3. To find the distinct integer pairs \\((r_1, r_2)\\) whose product is 36, we need to determine all pairs of integers \\((r_1, r_2)\\) such that \\( r_1 \\cdot r_2 = 36 \\) and \\( r_1 \\neq r_2 \\).\n\n4. From the equation \\( r_1 + r_2 = -k \\), for each valid pair \\((r_1, r_2)\\), we can compute the corresponding value of \\( k \\).\n\n5. Finally, since we need the polynomial to have two distinct integer roots, we need to ensure that \\( r_1 \\) and \\( r_2 \\) are distinct.\n\nLet's start by finding all pairs \\((r_1, r_2)\\) such that \\( r_1 \\cdot r_2 = 36 \\). We'll then determine the values of \\( k \\) and ensure the roots are distinct.\n```python\nimport itertools\n\n# Find all pairs (r1, r2) such that r1 * r2 = 36\nproduct_36 = 36\nfactor_pairs = []\n\nfor i in range(1, product_36 + 1):\n if product_36 % i == 0:\n pair = (i, product_36 // i)\n if pair[0] != pair[1]: # Ensure distinct pairs\n factor_pairs.append(pair)\n\n# Calculate k for each pair and ensure distinct integer roots\nvalid_k_values = set()\nfor r1, r2 in factor_pairs:\n if r1 != r2:\n k = -(r1 + r2)\n valid_k_values.add(k)\n\nprint((len(valid_k_values), sorted(valid_k_values)))\n```\n```output\n(4, [-37, -20, -15, -13])\n```\nThe distinct integer values of \\( k \\) that make the polynomial \\( x^2 + kx + 36 \\) have two distinct integer roots are \\(-37, -20, -15, \\text{and} -13\\).\n\nTherefore, the number of such values of \\( k \\) is:\n\n\\[\n\\boxed{4}\n\\]\n
+pipeline_tag: text-generation
+
+
 model-index:
-- name: aimo_v51.2
+- name: Numina-Math-7B
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# aimo_v51.2
+# Model Card for Numina-Math-7B
+
+Numina-Math is a series of language models that are trained to solve math problems using tool integrated reasoning.
+Numina-Math-7b won the first AI Math Olympiad, with a score of 29/50 on the public and private tests sets.
+This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) with two stages on Math Question answers and multi-step synthetic generations using tool integrated reasoning.
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6200d0a443eb0913fa2df7cc/NyhBs_gzg40iwL995DO9L.png)
 
-This model is a fine-tuned version of [AI-MO/deepseek-math-7b-sft](https://huggingface.co/AI-MO/deepseek-math-7b-sft) on the AI-MO/tora-chosen-v0.7 dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.5302
 
 ## Model description
 
-More information needed
+- **Model type:** A 7B parameter Math model fine-tuned in two stages on Math Question answers and multi-step synthetic generations using tool integrated reasoning.
+- **Language(s) (NLP):** Primarily English
+- **License:** MIT
+- **Finetuned from model:** [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base)
 
-## Intended uses & limitations
+### Model Sources
 
-More information needed
+<!-- Provide the basic links for the model. -->
 
-## Training and evaluation data
+- **Repository:** Coming soon to https://github.com/huggingface/alignment-handbook
+- **Demo:** https://huggingface.co/spaces/AI-MO/math-olympiad-solver
+
+## Intended uses & limitations
+
+Here's how you can run the model using the `pipeline()` function from 🤗 Transformers:
+
+```python
+# Install transformers from source - only needed for versions <= v4.34
+# pip install git+https://github.com/huggingface/transformers.git
+# pip install accelerate
+
+import torch
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-7b-beta", torch_dtype=torch.bfloat16, device_map="auto")
+
+# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
+messages = [
+    {
+        "role": "system",
+        "content": "You are a friendly chatbot who always responds in the style of a pirate",
+    },
+    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
+]
+prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+# <|system|>
+# You are a friendly chatbot who always responds in the style of a pirate.</s>
+# <|user|>
+# How many helicopters can a human eat in one sitting?</s>
+# <|assistant|>
+# Ah, me hearty matey! But yer question be a puzzler! A human cannot eat a helicopter in one sitting, as helicopters are not edible. They be made of metal, plastic, and other materials, not food!
+```
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+Numina-Math-7B was create to solve math problems, the model has not been align to preferences beyond the domain of solving math, and should not be used in a general chat setting.
 
-More information needed
 
 ## Training procedure
 
@@ -65,3 +120,18 @@ The following hyperparameters were used during training:
 - Pytorch 2.3.1
 - Datasets 2.18.0
 - Tokenizers 0.19.1
+
+## Citation
+
+If you find Numina-Math is useful in your work, please cite it with:
+
+```
+@misc{beeching2024numina-math,
+      title={Numina Math}, 
+      author={Edward Beeching and Lewis Tunstall and Roman Soletskyi and Kashif Rasul and Shengyi Huang and Jia Li},
+      year={2024},
+      publisher = {Hugging Face},
+      journal = {Hugging Face repository},
+      howpublished = {\url{https://huggingface.co/AI-MO/Numina-Math-7B}}
+}
+```