automerger/T3qM7-7B
LoRA-style vs chihoonlee10/T3Q-Mistral-Orca-Math-DPO. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, up_proj changed, in 31 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 93/96, Attention 0/128, lm_head 0/1
2 derivatives checked
- MaziyarPanahi/T3qM7-7B-GGUF: Quantization
- MaziyarPanahi/T3qm7xNeuralsirkrishna_T3qM7: Full fine-tune