OpenGVLab/InternVL3-14B

Full fine-tune vs OpenGVLab/InternVL3-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 5/5, Norms 147/193, MLP 238/246, Attention 432/432, other 0/48, lm_head 1/1

3 derivatives checked

• unsloth/InternVL3-14B-GGUF: Same weights, converted (fewer layers)
• mradermacher/InternVL3-14B-i1-GGUF: Quantization (fewer layers)
• mradermacher/InternVL3-14B-GGUF: Quantization (fewer layers)

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse