Cran-May/T.E-8.1
LoRA-style vs Qwen/Qwen2.5-7B-Instruct. 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
13 derivatives checked
- mradermacher/T.E-8.1-i1-GGUF: Quantization
- featherless-ai-quants/Cran-May-T.E-8.1-GGUF: Quantization
- mradermacher/T.E-8.1-GGUF: Same weights, converted
- Lewdiculous/T.E-8.1-GGUF-IQ-Imatrix-Request: Same weights, converted
- bunnycore/Qevacot-7B-v2: Full fine-tune
- suayptalha/Rombos-2.5-T.E-8.1: Full fine-tune
- bunnycore/QevaCoT-7B-Stock: Full fine-tune
- bunnycore/Qwen-2.5-7b-TitanFusion-v5-Exp: Full fine-tune
- bunnycore/Qevacot-7B: Full fine-tune
- ClaudioItaly/Chronicle-Qwen2.5-7B: Full fine-tune
- marcuscedricridia/Hush-Qwen2.5-7B-RP: Full fine-tune
- marcuscedricridia/Yell-Qwen2.5-7B-Stock: Full fine-tune
- bunnycore/Qwen-2.5-7b-TitanFusion-v2: Full fine-tune
1 other repos hold byte-for-byte identical weight files.