Hi, I've found out that Pythia (from EleutherAI) is better that Cerebras GPT in terms of evaluation results. Pythia is basically a LLM that based on GPT NeoX architecture but it's parameters ranging from 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B to 13B. Pythia itself is available in GitHub repository "EleutherAI/pythia" and Huggingface Models under the same name.
Does this project support Pythia based models? If no, any plans on supporting them afterwards? I appreciate the implementation of Pythia in this project. Thank you very much before.
Hi, I've found out that Pythia (from EleutherAI) is better that Cerebras GPT in terms of evaluation results. Pythia is basically a LLM that based on GPT NeoX architecture but it's parameters ranging from 70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B to 13B. Pythia itself is available in GitHub repository "EleutherAI/pythia" and Huggingface Models under the same name.
Does this project support Pythia based models? If no, any plans on supporting them afterwards? I appreciate the implementation of Pythia in this project. Thank you very much before.