Hi,
I have fined-tuned a llama-2-7b model on a text generation task using Colab Pro, GPU tested:: T4, and A100.
The instruction I used to push the model to the hub is: model.push_to_hub(“amr_my_llm_finetuned”)
Here is my model on the hub: royam0820/amr_my_llm_finetuned.
Here is the deployment endpoints: aws-amr-my-llm-finetuned-6755
During the deployment I have this error: OSError: /repository does not appear to have a file named config.json. Indeed, this file is missing.
Please let me know how to fix this issue. Can I simply add a config.json file from abhishek/llama-2-7b-hf-small-shards?
Thanks in advance for your help and support.
Anne-Marie