someone on Nostr: gemma 3 fine tuning was not as effective as llama 3. it responded well to my healthy ...
gemma 3 fine tuning was not as effective as llama 3. it responded well to my healthy living type of datasets and learned well. but in faith, fasting and misinformation type of domains, it got stuck and doesn't want to learn more. i guess LLMs can be stubborn too!
Published at
2025-04-30 14:53:39Event JSON
{
"id": "f32eb9cc79fe35bbe452c2e2d5fe071f1ab2c1f6a798d7d5406170eb90e0242e",
"pubkey": "9fec72d579baaa772af9e71e638b529215721ace6e0f8320725ecbf9f77f85b1",
"created_at": 1746024819,
"kind": 1,
"tags": [],
"content": "gemma 3 fine tuning was not as effective as llama 3. it responded well to my healthy living type of datasets and learned well. but in faith, fasting and misinformation type of domains, it got stuck and doesn't want to learn more. i guess LLMs can be stubborn too!",
"sig": "5f5e1d620e1b6b85fcc67d55b6dd1b8f1d3f3481bfd3be4da420c079b27b72f5d998b6012b5ef0c12ffe8adec4c966741fb29c2bad0dfd9fec31e85fd85c1461"
}
