Update README.md
Browse files
README.md
CHANGED
@@ -96,11 +96,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
96 |
|
97 |
# Model Card for NuminaMath 72B TIR
|
98 |
|
99 |
-
NuminaMath is a series of language models that are trained
|
100 |
-
|
101 |
-
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6200d0a443eb0913fa2df7cc/NyhBs_gzg40iwL995DO9L.png)
|
102 |
-
|
103 |
-
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 of supervised fine-tuning:
|
104 |
|
105 |
* **Stage 1:** fine-tune the base model on a large, diverse dataset of natural language math problems and solutions, where each solution is templated with Chain of Thought (CoT) to facilitate reasoning.
|
106 |
* **Stage 2:** fine-tune the model from Stage 1 on a synthetic dataset of tool-integrated reasoning, where each math problem is decomposed into a sequence of rationales, Python programs, and their outputs.
|
|
|
96 |
|
97 |
# Model Card for NuminaMath 72B TIR
|
98 |
|
99 |
+
NuminaMath is a series of language models that are trained with two stages of supervised fine-tuning to solve math problems using chain of thought (CoT) and tool-integrated reasoning (TIR):
|
|
|
|
|
|
|
|
|
100 |
|
101 |
* **Stage 1:** fine-tune the base model on a large, diverse dataset of natural language math problems and solutions, where each solution is templated with Chain of Thought (CoT) to facilitate reasoning.
|
102 |
* **Stage 2:** fine-tune the model from Stage 1 on a synthetic dataset of tool-integrated reasoning, where each math problem is decomposed into a sequence of rationales, Python programs, and their outputs.
|