DebateLabKIT
/

Phi-4-Argunaut-1-HIRPO

Text Generation

critical-thinking

argument-mapping

Generated from Trainer

text-generation-inference

Model card Files Files and versions

ggbetz commited on 12 days ago

Commit

69b99b6

·

verified ·

1 Parent(s): ff613f8

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ This model is a fine-tuned version of [DebateLabKIT/Phi-4-Argunaut-1-SPIN-dev1](
 It has been trained using [TRL](https://github.com/huggingface/trl).
-📘 [HF Blog Article](https://huggingface.co/blog/ggbetz/argunauts-phase-3)
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://api.wandb.ai/links/ggbetz/tqp681ch)
@@ -62,7 +62,7 @@ We have released the preference pairs generated online as a separate dataset: [D
 ## Evaluation
-🚧 coming soon
 ## Citations

 It has been trained using [TRL](https://github.com/huggingface/trl).
+📘 [HF Blog Article](https://huggingface.co/blog/ggbetz/argunauts-update-202512)
 [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://api.wandb.ai/links/ggbetz/tqp681ch)
 ## Evaluation
+As described in [this article](https://huggingface.co/blog/ggbetz/argunauts-update-202512), `Phi-4-Argunaut-1-HIRPO` technically masters formal argument analysis but has lost general conversational abilities during one-sided training.
 ## Citations