llm-bg/Tucan-27B-v1.0
LoRA-style vs INSAIT-Institute/BgGPT-Gemma-2-27B-IT-v1.0. 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 46 of 46 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/185, MLP 138/138, Attention 184/184
5 derivatives checked
- mradermacher/LLMBG-ToolUse-27B-v1.0-i1-GGUF: Quantization
- mradermacher/Tucan-27B-v1.0-i1-GGUF: Quantization
- mradermacher/Tucan-27B-v1.0-GGUF: Quantization
- llm-bg/Tucan-27B-v1.0-GGUF: Quantization
- mradermacher/LLMBG-ToolUse-27B-v1.0-GGUF: Quantization