ytu-ce-cosmos/Turkish-Llama-8b-DPO-v0.1
Full fine-tune vs ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 0/1, Embeddings 1/1, Norms 3/65, MLP 96/96, Attention 128/128
6 derivatives checked
- mradermacher/Turkish-Llama-8b-DPO-v0.1-GGUF: Same weights, converted
- ozertuu/Lama3.1-8B-EksiSozlukAI: LoRA-style
- oncu/Turkish-Llama-3-8B-function-calling-GGUF: Full fine-tune
- Metin/LLaMA-3-8B-GRPO-Finance-Math-TR: LoRA-style
- atasoglu/Turkish-Llama-3-8B-function-calling: LoRA-style
- RsGoksel/Lama3.1-8B-Saver-16B: LoRA-style
1 other repos hold byte-for-byte identical weight files.