Tuning Engines

List fine-tuning training jobs on Tuning Engines. Returns recent jobs with status, base model, agent type, GPU usage, and cost. Use this to check on existing training runs or find a job ID.

Get full details of a specific fine-tuning job including status, base model, agent type, GPU minutes, cost, error messages, and whether it can be retried from checkpoint.

Fine-tune an LLM on a GitHub repository using Tuning Engines. This trains a custom model that learns from the code patterns, style, and conventions in the repo. Choose an agent to control the training approach:

AVAILABLE AGENTS:

• agent='code_repo' (Cody) — LoRA-based code fine-tuning using QLoRA (4-bit quantized LoRA) via the Axolotl framework. Trains on your repo's code patterns, naming conventions, and project structure to produce a fast, lightweight adapter. Best for: code autocomplete, inline suggestions, tab-complete, code style matching.

• agent='sera_code_repo' (SIERA) — Bug-fix specialist using the Open Coding Agents approach from AllenAI. Generates synthetic error-resolution training pairs from your repo, producing a model that understands your codebase's failure patterns and fix conventions. Best for: debugging, error resolution, patch generation, root cause analysis. Supports quality_tier='low' (faster) or quality_tier='high' (deeper analysis, more training data).

SUPPORTED BASE MODELS (by size):

• 3B: Qwen/Qwen2.5-Coder-3B-Instruct

• 7B: codellama/CodeLlama-7b-hf, deepseek-ai/deepseek-coder-7b-instruct-v1.5, Qwen/Qwen2.5-Coder-7B-Instruct

• 13-15B: codellama/CodeLlama-13b-Instruct-hf, bigcode/starcoder2-15b, Qwen/Qwen2.5-Coder-14B-Instruct

• 32-34B: deepseek-ai/deepseek-coder-33b-instruct, codellama/CodeLlama-34b-Instruct-hf, Qwen/Qwen2.5-Coder-32B-Instruct

• 70-72B: codellama/CodeLlama-70b-Instruct-hf, meta-llama/Llama-3.1-70B-Instruct, Qwen/Qwen2.5-72B-Instruct

TYPICAL WORKFLOW: estimate_job first to check cost, then create_job, then job_status to monitor progress.

Cancel a running or queued fine-tuning job. The job will be charged for any GPU time already used.

Get live status of a fine-tuning job including current status, GPU minutes used, estimated charges, remaining balance, and delivery progress. Use this to monitor a running job.

Retry a failed fine-tuning job from its last checkpoint. Creates a new job that resumes training where the failed one stopped, saving GPU time. Each retry is billed separately.

Get a cost estimate for a fine-tuning job before submitting it. Returns estimated cost, cost range, current balance, and whether balance is sufficient. Always estimate before creating a job.

Validate S3 credentials by testing read/write access to the specified bucket. Use before submitting a job with S3 export.

List your trained and imported models on Tuning Engines.

Get details of a specific trained model.

Delete a trained model from cloud storage.

Check your Tuning Engines account balance and recent transactions.

Get your Tuning Engines account details and settings.

List the supported base HuggingFace models available for fine-tuning on Tuning Engines.

Import a model from S3 into Tuning Engines cloud storage so it can be used as a base for future fine-tuning jobs.

Export a trained model from Tuning Engines cloud storage to your S3 bucket.

Check the status of a model import or export operation.