DISLab/Ext2Gen-8B-R2
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 k_proj, 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 96/128, lm_head 0/1
2 derivatives checked
- featherless-ai-quants/DISLab-Ext2Gen-8B-R2-GGUF: Quantization
- mradermacher/Ext2Gen-8B-R2-GGUF: Same weights, converted