rawsh
/

mirrorqwen2.5-0.5b-SimPO-0

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

rawsh commited on 13 days ago

Commit

c699a3f

•

1 Parent(s): 6c5fd64

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/w0rqb42r)
 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/uo8om698)
 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 sha256:05d16fe1553358554cbc8ddc18ef259480871fc88aa27a3fa8214cccba421197
 size 988097536

 version https://git-lfs.github.com/spec/v1
+oid sha256:6a7050cb74023b2109da6cbfd40209130bde852f9fe13705ab80be1d0120ceb1
 size 988097536

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd9bfa8c4cb7904320aa425cbc2a9e97ec92eb74340bfb10a22daca613a959b
 size 5752

 version https://git-lfs.github.com/spec/v1
+oid sha256:e9a5dfeae851520644dee8a1ea876e6e429670dc43ff89a16d98ae5489a07d43
 size 5752