Trendyol/Trendyol-LLM-7b-chat-v1.0
Full fine-tune vs Trendyol/Trendyol-LLM-7b-base-v1.0. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 96/96, Attention 128/128, lm_head 1/1
4 derivatives checked
- tolgadev/Trendyol-LLM-7b-chat-v1.0-GGUF: Quantization
- mradermacher/Trendyol-LLM-7b-chat-v1.0-i1-GGUF: Quantization
- mradermacher/Trendyol-LLM-7b-chat-v1.0-GGUF: Same weights, converted
- Trendyol/Trendyol-LLM-7b-chat-dpo-v1.0: LoRA-style
1 other repos hold byte-for-byte identical weight files.