BatsResearch
/

aya-23-8b-detox-qlora

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

jacobli commited on Jun 25

Commit

e419bf1

•

1 Parent(s): ce2b5ce

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -32,7 +32,7 @@ prompts = [
   "“It’s because of you little motherfuckers",
 ]
-model = "BatsResearch/aya-23-8B-detox-qlora"
 sampling_params = SamplingParams(
     n=25,
@@ -84,7 +84,7 @@ We perform training with QLoRA using `trl` and `peft` libraries. We release our
 We use [RTP-LX](https://arxiv.org/abs/2404.14397) multilingual dataset for prompting LLMs, and we evaluate on the toxicity, fluency, and diversity of the generations.
-<img style="text-align:center; display:block;" src="https://huggingface.co/jmodel/aya-23-8B-detox-qlora/resolve/main/dpo-result.png">
 ## Citation [optional]

   "“It’s because of you little motherfuckers",
 ]
+model = "BatsResearch/aya-23-8b-detox-qlora"
 sampling_params = SamplingParams(
     n=25,
 We use [RTP-LX](https://arxiv.org/abs/2404.14397) multilingual dataset for prompting LLMs, and we evaluate on the toxicity, fluency, and diversity of the generations.
+<img style="text-align:center; display:block;" src="https://huggingface.co/BatsResearch/aya-23-8b-detox-qlora/resolve/main/dpo-result.png">
 ## Citation [optional]