Update README.md
Browse files
README.md
CHANGED
@@ -9,7 +9,7 @@ base_model:
|
|
9 |
# RDS+ Wildchat Tulu 2 326k
|
10 |
|
11 |
This is a model trained on 326k samples selected by RDS+ using wildchat samples from the [Tulu 2 unfiltered dataset](https://huggingface.co/datasets/hamishivi/tulu-2-unfiltered).
|
12 |
-
For more details, please see the paper [Practical Large-Scale Data Selection for Instruction Tuning](
|
13 |
|
14 |
<center>
|
15 |
<img src="https://huggingface.co/hamishivi/tulu-2-multitask-rrmax-326k-sft/resolve/main/image.png" alt="Practical Large-Scale Data Selection for Instruction Tuning logo" width="200px"/>
|
@@ -30,7 +30,7 @@ For more details, please see the paper [Practical Large-Scale Data Selection for
|
|
30 |
|
31 |
## Results
|
32 |
|
33 |
-
For more results and analysis, please see [our paper](
|
34 |
|
35 |
|
36 |
| Method | MMLU | GSM8k | BBH | TydiQA | Codex | Squad | AlpacaEval | Average |
|
@@ -82,7 +82,8 @@ If you find this model or data is useful in your work, please cite it with:
|
|
82 |
title={{Practical Large-Scale Data Selection for Instruction Tuning}},
|
83 |
author={{Hamish Ivison and Muru Zhang and Faeze Brahman and Pang Wei Koh and Pradeep Dasigi}}
|
84 |
year={2025},
|
85 |
-
|
|
|
86 |
archivePrefix={arXiv},
|
87 |
primaryClass={cs.CL}
|
88 |
}
|
|
|
9 |
# RDS+ Wildchat Tulu 2 326k
|
10 |
|
11 |
This is a model trained on 326k samples selected by RDS+ using wildchat samples from the [Tulu 2 unfiltered dataset](https://huggingface.co/datasets/hamishivi/tulu-2-unfiltered).
|
12 |
+
For more details, please see the paper [Practical Large-Scale Data Selection for Instruction Tuning](https://arxiv.org/abs/2503.01807) and [associated codebase](https://github.com/hamishivi/automated-instruction-selection).
|
13 |
|
14 |
<center>
|
15 |
<img src="https://huggingface.co/hamishivi/tulu-2-multitask-rrmax-326k-sft/resolve/main/image.png" alt="Practical Large-Scale Data Selection for Instruction Tuning logo" width="200px"/>
|
|
|
30 |
|
31 |
## Results
|
32 |
|
33 |
+
For more results and analysis, please see [our paper](https://arxiv.org/abs/2503.01807).
|
34 |
|
35 |
|
36 |
| Method | MMLU | GSM8k | BBH | TydiQA | Codex | Squad | AlpacaEval | Average |
|
|
|
82 |
title={{Practical Large-Scale Data Selection for Instruction Tuning}},
|
83 |
author={{Hamish Ivison and Muru Zhang and Faeze Brahman and Pang Wei Koh and Pradeep Dasigi}}
|
84 |
year={2025},
|
85 |
+
url={https://arxiv.org/abs/2503.01807},
|
86 |
+
eprint={2503.01807},
|
87 |
archivePrefix={arXiv},
|
88 |
primaryClass={cs.CL}
|
89 |
}
|