belyakoff/SmolLM2-360M-Instruct-FT
LoRA-style vs HuggingFaceTB/SmolLM2-360M-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 64/96, Attention 128/128
2 derivatives checked
- mradermacher/SmolLM2-360M-Instruct-FT-GGUF: Same weights, converted
- tensorblock/SmolLM2-360M-Instruct-FT-GGUF: Quantization