Hessa Alawwad

icon indicating an email [email protected]

icon location I am a PhD student specializing in natural language processing (NLP) with a focus on AI-driven solutions.

Results 4 comments of Hessa Alawwad

Can llama3.2 vision accept no image?

like in this: ``` question = row['Question'] options = row['AnswerChoices'] message = (f"Answer the question with the correct option letter. " f"Question: {question}\nOptions: {options}") messages = [ {"role": "user", "content":...

Can llama3.2 vision accept no image?

@ashwinb

Get the multimodal embeddings

Please bear with me if my questions does not make sense but I am still learning. I see after I give it an input consist of two modality ( text...

Train on completions only by fixing the collator inquiry

Thank you for your response @danielhanchen , but inputs must be text-only for train_on_responses_only right? What when working with multimodal models like llama3.2 what shall I do?