hummingbird2030

Results 5 comments of hummingbird2030

[Usage]: Problem when loading my trained model.

> I also meet the problem. Is there any solution? I fixed it by deleting the 'model.safetensors'. Hope to help you.

About parameter `max_depth`

Is it the max time steps when generating? I guess.

Cannot approach the performance of the uploaded self-rag ckpt when finetuning meta/Llama-2 myself

Hello , I encountered the same problem. I wonder how do you load the model. I have trained a model and get the same files, which have `model.safetensors `. I...

Cannot approach the performance of the uploaded self-rag ckpt when finetuning meta/Llama-2 myself

> I encountered the problem (`assert loaded_weight.shape[parallel_dim] == self.num_embeddings`), but I solved it by deleting the file `model.safetensors` ... Thanks, I solved this problem the same!

Retrieval-augmented baselines - Huggingface models

> and I run the example about PubHealth， python run_baseline_lm.py \ > > > --model_name meta-llama/Llama-2-7b-hf > > --input_file eval_data/health_claims_processed.jsonl > > --max_new_tokens 20 > > --metric accuracy > >...