amberyzheng
/

qwen2.5-7b-trl-sft-500

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Community

amberyzheng commited on 19 days ago

Commit

67b1911

·

verified ·

1 Parent(s): aea1884

Model save

Files changed (2) hide show

README.md +1 -1
adapter_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ 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/zhengyjzoe/qwen2.5-7b-instruct-trl-sft-Webpage/runs/r9fbqfo1)
 This model was trained with SFT.

 ## 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/zhengyjzoe/Accessible-VLM/runs/kflsjsj6)
 This model was trained with SFT.

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee497acdc9b8db85001c8e43c87db118619905f8c1f729b283afa5b90fc7b2b
 size 10107280

 version https://git-lfs.github.com/spec/v1
+oid sha256:ada64d3209c5d4fc0096895bf4ff103f494c44f7dcb02460b98239b63219d0d9
 size 10107280