prithivMLmods/Calcium-Opus-14B-Elite2-R1
LoRA-style vs prithivMLmods/Calcium-Opus-14B-Elite2. 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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 144/144, Attention 192/336, lm_head 0/1
6 derivatives checked
- mradermacher/Calcium-Opus-14B-Elite2-R1-i1-GGUF: Quantization
- mradermacher/Calcium-Opus-14B-Elite2-R1-GGUF: Quantization
- DevQuasar-8/prithivMLmods.Calcium-Opus-14B-Elite2-R1-GGUF: Same weights, converted
- prithivMLmods/Megatron-Opus-14B-Stock: Full fine-tune
- prithivMLmods/Delta-Pavonis-Qwen-14B: Full fine-tune
- prithivMLmods/Primal-Opus-14B-Optimus-v1: Full fine-tune