rawsh
/

mirrorqwen2.5-0.5b-ORPO-2

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

rawsh commited on 17 days ago

Commit

e17b0dd

•

1 Parent(s): 83ca9ec

Model save

Files changed (3) hide show

README.md +1 -1
model.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -28,7 +28,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/dankgpt/orpo-training/runs/gspz6nyl)
 This model was trained with ORPO, a method introduced in [ORPO: Monolithic Preference Optimization without Reference Model](https://huggingface.co/papers/2403.07691).

 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/dankgpt/orpo-training/runs/u3uw2te2)
 This model was trained with ORPO, a method introduced in [ORPO: Monolithic Preference Optimization without Reference Model](https://huggingface.co/papers/2403.07691).

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a536ba802b6bea2b46e28b4e3d033712b4c42b18e870693154879ad85387e83
 size 988097536

 version https://git-lfs.github.com/spec/v1
+oid sha256:49174cd00e88ecf484859b7fddb123e1860cf8fcf200d5e434bbfb7a45abfa61
 size 988097536

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9e5bd90f259dcfd090a59cb4b7ecc2b169617c1c7e8c8d711ad410e50628328
 size 5560

 version https://git-lfs.github.com/spec/v1
+oid sha256:95c005bad6e44b33ee55f82999d2881996d27def9abf110a8b6225aabac0ba4c
 size 5560