Hugging Face's logo

nvidia
/
AceMath-7B-Instruct

Text Generation
Safetensors
PyTorch
English
qwen2
nvidia
AceMath
math
CoT
conversational
Model card Files Community
zihanliu commited on
Commit
8fcf91b
·
verified ·
1 Parent(s): 5689fb0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -5
README.md CHANGED
@@ -23,16 +23,20 @@ For more information about AceMath, check our [website](https://research.nvidia.
23
 
24
 
25
  ## All Resources
26
- [AceMath-1.5B-Instruct](https://huggingface.co/nvidia/AceMath-1.5B-Instruct)   [AceMath-7B-Instruct](https://huggingface.co/nvidia/AceMath-7B-Instruct)   [AceMath-72B-Instruct](https://huggingface.co/nvidia/AceMath-72B-Instruct)
 
27
 
28
- [AceMath-7B-RM](https://huggingface.co/nvidia/AceMath-7B-RM)   [AceMath-72B-RM](https://huggingface.co/nvidia/AceMath-72B-RM)   [AceMath-RewardBench](https://huggingface.co/datasets/nvidia/AceMath-RewardBench)
 
29
 
30
- [AceMath-Instruct Training Data](https://huggingface.co/datasets/nvidia/AceMath-Instruct-Training-Data)   [AceMath-RM Training Data](https://huggingface.co/datasets/nvidia/AceMath-RM-Training-Data)
 
31
 
32
- [AceInstruct-1.5B](https://huggingface.co/nvidia/AceInstruct-1.5B)   [AceInstruct-7B](https://huggingface.co/nvidia/AceInstruct-7B)   [AceInstruct-72B](https://huggingface.co/nvidia/AceInstruct-72B)
 
33
 
34
 
35
- ## Benchmark Results
36
 
37
  <p align="center">
38
  <img src="https://research.nvidia.com/labs/adlr/images/acemath/acemath.png" alt="AceMath Benchmark Results" width="800">
 
23
 
24
 
25
  ## All Resources
26
+ ### AceMath Instruction Models
27
+ - [AceMath-1.5B-Instruct](https://huggingface.co/nvidia/AceMath-1.5B-Instruct), [AceMath-7B-Instruct](https://huggingface.co/nvidia/AceMath-7B-Instruct), [AceMath-72B-Instruct](https://huggingface.co/nvidia/AceMath-72B-Instruct)
28
 
29
+ ### AceMath Reward Models
30
+ - [AceMath-7B-RM](https://huggingface.co/nvidia/AceMath-7B-RM), [AceMath-72B-RM](https://huggingface.co/nvidia/AceMath-72B-RM)
31
 
32
+ ### Evaluation & Training Data
33
+ - [AceMath-RewardBench](https://huggingface.co/datasets/nvidia/AceMath-RewardBench), [AceMath-Instruct Training Data](https://huggingface.co/datasets/nvidia/AceMath-Instruct-Training-Data), [AceMath-RM Training Data](https://huggingface.co/datasets/nvidia/AceMath-RM-Training-Data)
34
 
35
+ ### General Instruction Models
36
+ - [AceInstruct-1.5B](https://huggingface.co/nvidia/AceInstruct-1.5B), [AceInstruct-7B](https://huggingface.co/nvidia/AceInstruct-7B), [AceInstruct-72B](https://huggingface.co/nvidia/AceInstruct-72B)
37
 
38
 
39
+ ## Benchmark Results (AceMath-Instruct + AceMath-72B-RM)
40
 
41
  <p align="center">
42
  <img src="https://research.nvidia.com/labs/adlr/images/acemath/acemath.png" alt="AceMath Benchmark Results" width="800">