How to train your own Jev for $17
Sep 23, 2026
Summary
This post details the practical steps for fine-tuning a Qwen3.5 4B model for classification tasks. It covers dataset preparation by sampling from multiple Hugging Face datasets (MultiNLI, BoolQ, Banking77, AG News, SST-5, Programmatic policies, Routing, Research taxonomy), normalization using provided Python scripts, launching a fine-tuning job via the Together AI service, and deploying the trained model to a dedicated endpoint. It also provides an example of querying the deployed model with a JSON payload for classification and outlines the necessary API parameters for direct calls.
More from the Fine-Tuning Platform trail
- Together AI expands fine-tuning service with more models, live metrics, and finer controls
- DeepSeek-V4 Flash 0731 vs GPT-5.6 Luna on DeepSWE: Cost and Coding
- Accelerate RL rollouts by up to 50% with distribution-aware speculative decoding
- Together AI expands fine-tuning service with tool calling, reasoning, and vision support
- Fine-tuning open LLM judges to outperform GPT-5.2