Trendyol/Trendyol-LLM-7b-base-v1.0
LoRA-style vs mistralai/Mistral-7B-v0.1. 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: Norms 0/65, MLP 96/96, Attention 128/128
4 derivatives checked
- mradermacher/Trendyol-LLM-7b-base-v1.0-i1-GGUF: Quantization
- mradermacher/Trendyol-LLM-7b-base-v1.0-GGUF: Same weights, converted
- Trendyol/Trendyol-LLM-7b-chat-v1.0: Full fine-tune
- alperiox/Trendyol-LLM-7b-gguf-v1.0: Quantization