ZeusLabs/Chronos-Divergence-33B
LoRA-style vs elinas/chronos-33b. 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 60 of 60 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/121, MLP 180/180, Attention 240/240
3 derivatives checked
- bartowski/Chronos-Divergence-33B-GGUF: Same weights, converted
- mradermacher/Chronos-Divergence-33B-i1-GGUF: Quantization
- mradermacher/Chronos-Divergence-33B-GGUF: Quantization