ogulcanaydogan/Turkish-LLM-32B-Instruct
LoRA-style vs Qwen/Qwen2.5-32B-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 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 192/192, Attention 256/448, lm_head 0/1
3 derivatives checked
- ogulcanaydogan/Turkish-LLM-32B-Instruct-GGUF: Full fine-tune
- mradermacher/Turkish-LLM-32B-Instruct-i1-GGUF: Quantization
- mradermacher/Turkish-LLM-32B-Instruct-GGUF: Full fine-tune