Update README.md
Browse files
README.md
CHANGED
|
@@ -41,6 +41,15 @@ The models are evaluated using open-ended and multiple-choice math problems from
|
|
| 41 |
|
| 42 |
To reproduce our results, please refer to https://github.com/TIGER-AI-Lab/MAmmoTH2/tree/main/math_eval.
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
|
| 45 |
## Usage
|
| 46 |
You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution.
|
|
|
|
| 41 |
|
| 42 |
To reproduce our results, please refer to https://github.com/TIGER-AI-Lab/MAmmoTH2/tree/main/math_eval.
|
| 43 |
|
| 44 |
+
## Chat Format
|
| 45 |
+
|
| 46 |
+
The template used to build a prompt for the Instruct model is defined as follows:
|
| 47 |
+
```
|
| 48 |
+
<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]
|
| 49 |
+
```
|
| 50 |
+
Note that `<s>` and `</s>` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.
|
| 51 |
+
|
| 52 |
+
But we also found that the model is not very sensitive to the chat template.
|
| 53 |
|
| 54 |
## Usage
|
| 55 |
You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution.
|