YAML Metadata Warning: empty or missing yaml metadata in repo card
Check out the documentation for more information.
About model
This model pretrain_768_run-01.pth was trained with pytroch from scratch.
- pretrain means this is a base model without instruction fine-tuning.
- 768 means the embedding size of this model is 768 dimensions.
- run-01 represents the run name that you can find in wandb.
Usage
To run the model:
- git clone zhiqiang-repo
- go to file scripts/pretrain/eval_pretrain.sh
- change the model path where you download the model
- (optional) change the hyperparameters
- run and evaluate the model
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support