nielsr HF Staff commited on
Commit
f9528b9
·
verified ·
1 Parent(s): 0f9db81

Add pipeline tag and link to OpenCodeReasoning paper

Browse files

This PR adds the `pipeline_tag` to the metadata to increase discoverability. It also adds a direct link to the Hugging Face paper page for the model and states that this model is described in the OpenCodeReasoning paper.

Files changed (1) hide show
  1. README.md +8 -5
README.md CHANGED
@@ -1,22 +1,23 @@
1
  ---
2
- license: llama3.1
3
  base_model:
4
  - meta-llama/Llama-3.1-8B
5
  datasets:
6
  - nvidia/OpenMathInstruct-2
7
  language:
8
  - en
 
 
 
9
  tags:
10
  - nvidia
11
  - math
12
- library_name: transformers
13
  ---
14
 
15
  # OpenMath2-Llama3.1-8B
16
 
17
- OpenMath2-Llama3.1-8B is obtained by finetuning [Llama3.1-8B-Base](https://huggingface.co/meta-llama/Llama-3.1-8B) with [OpenMathInstruct-2](https://huggingface.co/datasets/nvidia/OpenMathInstruct-2).
18
 
19
- The model outperforms [Llama3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on all the popular math benchmarks we evaluate on, especially on [MATH](https://github.com/hendrycks/math) by 15.9%.
20
 
21
  <!-- <p align="center">
22
  <img src="scaling_plot.jpg" width="350"><img src="math_level_comp.jpg" width="350">
@@ -81,7 +82,9 @@ pipeline = transformers.pipeline(
81
  messages = [
82
  {
83
  "role": "user",
84
- "content": "Solve the following math problem. Make sure to put the answer (and only answer) inside \\boxed{}.\n\n" +
 
 
85
  "What is the minimum value of $a^2+6a-7$?"},
86
  ]
87
 
 
1
  ---
 
2
  base_model:
3
  - meta-llama/Llama-3.1-8B
4
  datasets:
5
  - nvidia/OpenMathInstruct-2
6
  language:
7
  - en
8
+ library_name: transformers
9
+ license: llama3.1
10
+ pipeline_tag: text-generation
11
  tags:
12
  - nvidia
13
  - math
 
14
  ---
15
 
16
  # OpenMath2-Llama3.1-8B
17
 
18
+ OpenMath2-Llama3.1-8B is obtained by finetuning [Llama3.1-8B-Base](https://huggingface.co/meta-llama/Llama-3.1-8B) with [OpenMathInstruct-2](https://huggingface.co/datasets/nvidia/OpenMathInstruct-2). This model is described in the paper [OpenCodeReasoning: Advancing Data Distillation for Competitive Coding](https://huggingface.co/papers/2504.01943).
19
 
20
+ The model outperforms [Llama3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on all the popular math benchmarks we evaluate on, especially on [MATH](https://github.com/hendrycks/math) by 15.9%.
21
 
22
  <!-- <p align="center">
23
  <img src="scaling_plot.jpg" width="350"><img src="math_level_comp.jpg" width="350">
 
82
  messages = [
83
  {
84
  "role": "user",
85
+ "content": "Solve the following math problem. Make sure to put the answer (and only answer) inside \\boxed{}.
86
+
87
+ " +
88
  "What is the minimum value of $a^2+6a-7$?"},
89
  ]
90