PORTULAN/gervasio-8b-portuguese-ptpt-decoder
LoRA-style vs meta-llama/Llama-3.1-8B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 64/128, lm_head 0/1
3 derivatives checked
- mradermacher/gervasio-8b-portuguese-ptpt-decoder-i1-GGUF: Quantization
- mradermacher/gervasio-8b-portuguese-ptpt-decoder-GGUF: Same weights, converted
- PORTULAN/gervasio-8b-portuguese-ptpt-decoder-quantized-4bit: Quantization