HuggingFaceTB/SmolVLM2-256M-Video-Instruct
Full fine-tune vs HuggingFaceTB/SmolVLM-256M-Instruct. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: lm_head 1/1, other 1/1, Embeddings 4/4, Norms 98/111, MLP 138/138, Attention 216/216
6 derivatives checked
- ggml-org/SmolVLM2-256M-Video-Instruct-GGUF: Same weights, converted (fewer layers)
- gaianet/SmolVLM2-256M-Video-Instruct-GGUF: Same weights, converted (fewer layers)
- mradermacher/SmolVLM2-256M-Video-Instruct-i1-GGUF: Quantization (fewer layers)
- second-state/SmolVLM2-256M-Video-Instruct-GGUF: Same weights, converted (fewer layers)
- mradermacher/SmolVLM2-256M-Video-Instruct-GGUF: Same weights, converted (fewer layers)
- lewiswatson/Frame2KG-SmolVLM-256m-JSON: LoRA-style (fewer layers)