nbeerbower/Dumpling-Mistral-Nemo-8B
LoRA-style vs nbeerbower/mistral-nemo-kartoffel-PRUNE3. 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 26 of 26 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/53, MLP 78/78, Attention 104/104
2 derivatives checked
- mradermacher/Dumpling-Mistral-Nemo-8B-i1-GGUF: Quantization
- mradermacher/Dumpling-Mistral-Nemo-8B-GGUF: Same weights, converted