DavidAU/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL
LoRA-style vs Qwen/Qwen2.5-7B-Instruct-1M. 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 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 84/84, Attention 112/196, lm_head 0/1
4 derivatives checked
- mradermacher/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-i1-GGUF: Quantization
- mradermacher/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-GGUF: Same weights, converted
- alexgusevski/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-mlx-fp16: Same weights, converted
- MuXodious/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-PaperWitch-heresy: Abliterated