BeaverAI/MN-2407-DSK-QwQify-v0.1-12B
LoRA-style vs PocketDoc/Dans-SakuraKaze-V1.0.0-12b. 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 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 120/120, Attention 160/160, lm_head 0/1
5 derivatives checked
- bartowski/BeaverAI_MN-2407-DSK-QwQify-v0.1-12B-GGUF: Same weights, converted
- tensorblock/MN-2407-DSK-QwQify-v0.1-12B-GGUF: Quantization
- Disya/Mistral-qwq-12b-merge: Full fine-tune
- EldritchLabs/Cactus-Dream-Horror-12B: Full fine-tune
- Yobenboben/MN-12B-Paskuda: Full fine-tune