janhq/Jan-code-4b
Full fine-tune vs janhq/Jan-v3-4B-base-instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, MLP 108/108, Norms 71/145, Attention 144/144
5 derivatives checked
- janhq/Jan-code-4b-gguf: Quantization
- bartowski/janhq_Jan-code-4b-GGUF: Same weights, converted
- mradermacher/Jan-code-4b-i1-GGUF: Quantization
- mradermacher/Jan-code-4b-GGUF: Same weights, converted
- nbeerbower/Hemlock-Jan-code-4B: LoRA-style