This model was fine-tuned on CoT-style reasoning traces. The model will respond with a thinking trace between the and tags. The final answer will be between the and tags. Compared to the base Llama model, this thinker model has a tendency to generate a large number of tokens. So, if you are benchmarking make sure you have the full generated text in the reponse, ending with the tag. For most queries, you will need to set the maxtokens` to at least 8192. The GGUF quants for the model are available here — Llama-3.3-70B-o1-gguf The model was trained using QLoRA fine-tuning. You can find the adapter here — Llama-3.3-70B-o1-lora. — Developed by: codelion — License: apache-2.0 — Finetuned from model : unsloth/llama-3.3-70b-instruct-bnb-4bit This llama model was trained 2x faster with Unsloth and Huggingface’s TRL library.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: codelion
Теги: llama, text-generation-inference, unsloth, trl, conversational, en, endpoints_compatible
Лайков: 3 | Загрузок: 28
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
