At RefinedNeuro, we believe that the power of language models should be available to everyone, not just those with deep pockets or access to high end infrastructure. We envision a future where everyone can harness the potential of advanced AI models.
-
RN_TR_R2
RN_TR_R2 is a Turkish-language reasoning model fine-tuned from Turkish-Llama-8B using GRPO. It excels in STEM and cultural Q&A tasks, scoring 82.4% on benchmarks. Ideal for education-focused reasoning in Turkish.
tools2,956 Pulls 3 Tags Updated 4 months ago
-
RN_TR_R1
Bilingual Turkish-English LLaMA-based chat model. Optimized for instruction-following, reasoning, and real-time inference. Fine-tuned with Unsloth + TRL. Turkish-first, English-capable .Specially tuned for reasoning and logic. 2x faster training w/ Unslot
tools2,406 Pulls 3 Tags Updated 5 months ago
-
Turkcell-LLM-7b-v1
Turkcell-LLM-7b-v1 is a Turkish-optimized large language model based on Mistral 7B, fine-tuned with DORA and LORA methods on 5 billion Turkish tokens. Designed for robust natural language understanding and generation, it features an extended tokenizer
530 Pulls 3 Tags Updated 6 months ago