Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0
LoRA-style vs Trendyol/Trendyol-LLM-7b-chat-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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 0/1
3 derivatives checked
- tolgadev/Trendyol-LLM-7b-chat-dpo-v1.0-GGUF: Quantization
- mradermacher/Trendyol-LLM-7b-chat-dpo-v1.0-i1-GGUF: Quantization
- mradermacher/Trendyol-LLM-7b-chat-dpo-v1.0-GGUF: Same weights, converted