Arnav Chavan

The variables not used in the graph are not supported and gives a runtime error - RuntimeError: One of the differentiated Tensors appears to not have been used in the...

Can you share the model architecture for miniimagnet used in iMAML, since it varies slightly from paper to paper.

Evaluation of lit-llama models

8

Hello Team, Great work! I wanted to know whether https://github.com/Lightning-AI/lm-evaluation-harness/tree/lit-llama works or not since it is recently updated. If not is there any way I can evaluate lit-llama models on...

Bradley-Terry model removes lm head while saving

1

Hello and thanks for your work! While running bradley-terry-rm/llama3_rm.py the final saved model does not have a lm head as the script is using a AutoModelForSequenceClassification model and not CausalLM....

Phi3 has a nearly constant DPO loss of 0.69xx

6

### Issue: Implementing Iterative DPO on Phi3-4k-instruct Hi, thanks for the great work and open source! I am trying to implement iterative DPO on `Phi3-4k-instruct`. The following outlines my approach:...

Details of LoRA of pruned models.

6

Great work and thanks for the codebase! I want to know the exact detailed of LoRA fine-tuning as mentioned in Table 6 of the main paper. Also if you could...