trollek/LittleInstructionMaker-4B-v0.1

Full fine-tune vs h2oai/h2o-danube3-4b-base. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Norms 31/49, MLP 72/72, Attention 96/96

2 derivatives checked

• mradermacher/LittleInstructionMaker-4B-v0.1-GGUF: Same weights, converted
• trollek/LittleInstructionMaker-4B-v0.2: Full fine-tune

On the Hub · Downloads on Model Pulse