Need asistance fine tuning my model.

---

---

I'm looking for an experienced machine learning engineer who can personally guide me via Zoom or Splashtop through the successful fine-tuning and testing of a Qwen 14B Instruct Uncensored model. This is not a LoRA job. We're training full model weights in FP16. The base YAML configuration and dataset are already prepared — the challenge is orchestration and system setup (e.g., DeepSpeed/FSDP configs, launch stability, runtime troubleshooting). What I Need Help With: Reviewing and finalizing my training config (YAML, scripts, or Axolotl-style setup) Launching fine-tuning successfully on 2× H100 (or equivalent setup) Debugging environment issues (dependency conflicts, CUDA errors, memory tuning, etc.) Running test inference after training All of this live, over Zoom or Splashtop- you'll control, and we will record session. You Should Have: Proven experience launching full-weight fine-tunes (not LoRA) Familiarity with Qwen models, DeepSpeed, or FSDP Ability to troubleshoot Python, CUDA, and runtime environments quickly Clear communication skills — and the patience to walk me through the steps Session Format: We’ll share screens via Zoom or Splashtop I’ll be running things locally or on a rented cloud machine (RunPod, Lambda Labs, or similar) You’ll coach and debug live, as we walk through the setup

Keyword: Data Analysis

Price: $25.0

AI Development AI Model Training Model Tuning Machine Learning Python