This model is a fine-tuned version of unsloth/Meta-Llama-3.1-8B optimized for Text-to-SQL generation tasks. The fine-tuning was done using the Unsloth library with LoRA (Low-Rank Adaptation) for parameter-efficient fine-tuning. The training data consists of the first 5000 rows of the Clinton/Text-to-sql-v1 dataset. — Developed by: Vedant Rajpurohit — Model type: Causal Language Model — Language(s): English — Fine-tuned from model: unsloth/Meta-Llama-3.1-8B — Model size: 8.03B parameters — Precision: BF16 This model was fine-tuned by Vedant Rajpurohit using Meta-Llama 3.1-8B and the Clinton/Text-to-sql-v1 dataset. If you use this model or convert it to GGUF/quantized formats, a mention or backlink is appreciated 💛 For GGUF ports, see: — TensorBlock’s GGUF — mradermacher’s i-matrix quant — JHJHJHJHJ’s Q5KM GGUF — The model was only trained on first 5000 rows for 250 steps. — The model may generate incorrect or ambiguous SQL queries for instructions that are unclear or outside the training distribution. — Dataset Name: Clinton/Text-to-sql-v1 — Rows Used: First 5000 rows of the dataset. The model was fine-tuned using the Unsloth library with LoRA adapters, enabling efficient training.…
Модальности:
Генерация текста
Области применения:
Текст в SQL
Задача: Генерация текста
Автор: Vedant3907
Теги: llama, unsloth, trl, sft, en, text-generation-inference, endpoints_compatible
Лайков: 3 | Загрузок: 32
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
