Sakalti/SJT-2B

Same weights, converted vs google/gemma-2-2b-jpn-it. Same weights stored in another dtype (BF16 → F16).

Tensors changed: Embeddings 0/1, Norms 0/105, MLP 0/78, Attention 0/104

3 derivatives checked

• mradermacher/SJT-2B-i1-GGUF: Quantization
• mradermacher/SJT-2B-GGUF: Same weights, converted
• Sakalti/bonsai-2b: Full fine-tune

On the Hub · Downloads on Model Pulse