Ayansk11/FinSenti-SmolLM-1.7B
LoRA-style vs HuggingFaceTB/SmolLM-1.7B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 24 of 24 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 72/72, Attention 96/96
2 derivatives checked
- mradermacher/FinSenti-SmolLM-1.7B-GGUF: Same weights, converted
- Ayansk11/FinSenti-SmolLM-1.7B-GGUF: Quantization