Issues
- 0
Merge Issue ? My config.json has "Architecture" as "LlamaForCausalLM" instead of "LlavaLlamaForCausalLM" in the final merged and adapter models created
#6 opened by SrikanthChellappa - 9
tokenization mismatch
#1 opened by dingtine - 1
TypeError: Accelerator.__init__() got an unexpected keyword argument 'use_seedable_sampler'
#5 opened by SrikanthChellappa - 1
[Warning message] UserWarning: None of the inputs have requires_grad=True. Gradients will be None
#4 opened by y-rok - 1
pretrain llava1.6?
#3 opened by lightmatmul - 2
Compatible with LoRA finetune
#2 opened by Sprinter1999