g023dev
g023
AI & ML interests
ai datasets, ai training,ai software
Recent Activity
repliedto DedeProGames's post 10 days ago
Can small models program?
Although even if they are reasoning AIs, small AIs cannot create extensive and high-quality code, at least that's what is commonly thought.
We present https://huggingface.co/OrionLLM/NanoCoder-0.6b, an AI with just 600 million parameters based on qwen3-0.6b and trained with the dataset https://huggingface.co/datasets/nvidia/OpenCodeReasoning.
While not good at complex code, we observed a significant improvement in code generation (especially in Python code), demonstrating that, when trained correctly, small AIs can, in fact, program. reacted to DedeProGames's post with 🤗 10 days ago
Can small models program?
Although even if they are reasoning AIs, small AIs cannot create extensive and high-quality code, at least that's what is commonly thought.
We present https://huggingface.co/OrionLLM/NanoCoder-0.6b, an AI with just 600 million parameters based on qwen3-0.6b and trained with the dataset https://huggingface.co/datasets/nvidia/OpenCodeReasoning.
While not good at complex code, we observed a significant improvement in code generation (especially in Python code), demonstrating that, when trained correctly, small AIs can, in fact, program. updated a model 10 days ago
g023/Qwen3-1.77B-g023-GGUFOrganizations
None yet