Update README.md
Browse files
README.md
CHANGED
@@ -68,13 +68,12 @@ We are launching the large version of this model soon. Sign up [here](https://ww
|
|
68 |
|
69 |
Selene Mini can be used as a **general-purpose evaluation model**. It supports different inputs & scoring scales, generates structured evaluation outputs, and provides qualitative critiques with reasoning.
|
70 |
|
71 |
-
Try our cookbooks to get started with
|
72 |
|
73 |
-
- [
|
74 |
-
- [
|
75 |
-
- [Direct scoring](placeholder)
|
76 |
|
77 |
-
To achieve best results, **we provide the prompts we used for training [here](
|
78 |
|
79 |
Remember to apply the conversation template of Llama 3 - not doing so might lead to unexpected behaviors. You can find the conversation class at this [link](https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py) or you can refer to the below code that will apply it.
|
80 |
|
@@ -104,16 +103,4 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
|
104 |
|
105 | |
106 |
<br>
|
107 |
-
You can also join our [Discord](https://discord.com/invite/qFCMgkGwUK)!
|
108 |
-
|
109 |
-
## Citation
|
110 |
-
If you would like to cite our work, please cite using
|
111 |
-
|
112 |
-
```
|
113 |
-
@article{placeholder,
|
114 |
-
title={Atla Selene Mini: A General Purpose Evaluation Model},
|
115 |
-
author={Alexandru, Andrei and Calvi, Antonia and Broomfield, Henry and Golden, Jackson and Dai, Kyle and Leys, Mathias and Burger, Maurice and Bartolo, Max and Engeler, Roman and Pisupati, Sashank and Drane, Toby and Park, Young Sun},
|
116 |
-
journal={arXiv preprint arXiv:placeholder},
|
117 |
-
year={2025}
|
118 |
-
}
|
119 |
-
```
|
|
|
68 |
|
69 |
Selene Mini can be used as a **general-purpose evaluation model**. It supports different inputs & scoring scales, generates structured evaluation outputs, and provides qualitative critiques with reasoning.
|
70 |
|
71 |
+
Try our cookbooks to get started with two popular use cases below:
|
72 |
|
73 |
+
- [Absolute scoring](https://colab.research.google.com/github/atla-ai/selene-mini/blob/main/cookbooks/HF_Quickstart_Absolute_Scoring.ipynb)
|
74 |
+
- [RAG hallucination](https://colab.research.google.com/github/atla-ai/selene-mini/blob/main/cookbooks/HF_Quickstart_Hallucination.ipynb)
|
|
|
75 |
|
76 |
+
To achieve best results, **we provide the prompts we used for training [here](https://github.com/atla-ai/selene-mini/tree/main/prompt-templates).**
|
77 |
|
78 |
Remember to apply the conversation template of Llama 3 - not doing so might lead to unexpected behaviors. You can find the conversation class at this [link](https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py) or you can refer to the below code that will apply it.
|
79 |
|
|
|
103 |
|
104 | |
105 |
<br>
|
106 |
+
You can also join our [Discord](https://discord.com/invite/qFCMgkGwUK)!
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|