rawsh
/

mirrorqwen2.5-0.5b-SimPO-1

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

rawsh commited on Nov 11, 2024

Commit

9e6d259

·

verified ·

1 Parent(s): 4ba0613

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/simpo-training/runs/qmnc58lj)
 This model was trained with CPO, a method introduced in [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://huggingface.co/papers/2401.08417).

 ## 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/simpo-training/runs/tq03rlku)
 This model was trained with CPO, a method introduced in [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://huggingface.co/papers/2401.08417).

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24bf01aa2dcb7951e95b1f8bf451e976c8be2e142aef4349b773a1967cff7c3e
 size 988097536

 version https://git-lfs.github.com/spec/v1
+oid sha256:8ab05ebda0ded1d4a941a238f3985116542c4df0416ce8638c123e2f325ab03e
 size 988097536

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1bcbda931e8b55b9763db469ca7800b1dd02fee5633612e3a257472290bffe2
 size 5752

 version https://git-lfs.github.com/spec/v1
+oid sha256:d5ffb413cf8655a67384366791d59ab2832a73dd6c5dc3e1c32fa96450a719fb
 size 5752