Orion-zhen/Meissa-Qwen2.5-7B-Instruct
LoRA-style vs Orion-zhen/Qwen2.5-7B-Instruct-Uncensored. 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
7 derivatives checked
- mradermacher/Meissa-Qwen2.5-7B-Instruct-i1-GGUF: Quantization
- mradermacher/Meissa-Qwen2.5-7B-Instruct-GGUF: Same weights, converted
- yemiao2745/Meissa-Qwen2.5-7B-Instruct-Q4_K_M-GGUF: Quantization
- featherless-ai-quants/Orion-zhen-Meissa-Qwen2.5-7B-Instruct-GGUF: Quantization
- Orion-zhen/Meissa-Qwen2.5-7B-Instruct-Q5_K_M-GGUF: Quantization
- win10/high-speed-mixing-7B-V2: Full fine-tune
- win10/Meissa-Qwen2.5-12.3B-Instruct: Partial fine-tune (fewer layers)
1 other repos hold byte-for-byte identical weight files.