Home › Datasets › Function & Tool Calling

How to Fine-Tune an LLM for Function Calling & Tool Use

Selecting the correct tool/function, formatting calls correctly, and handling tool results appropriately.

• 994 instruction-response pairs
• Format JSONL
• Pack Agents & Tool Use
• Dataset $35 one-time

$35 for the dataset. Training is priced separately by model, starting at $47.

What can this kind of fine-tuning teach an LLM?

A general-purpose model may already know some of this subject. Fine-tuning serves a different purpose: it repeatedly demonstrates the kinds of requests, response patterns, terminology, decisions and workflows you want the model to handle more consistently.

For Function & Tool Calling, the dataset focuses on selecting the correct tool/function, formatting calls correctly, and handling tool results appropriately. Fine-tuning shapes recurring model behavior; it does not turn the model into a live database or guarantee correctness on every new case.

What training data should cover

Useful supervised fine-tuning data should resemble the work you expect the model to perform. This Rebiha dataset's domain definition is organized around 13 coverage areas:

• selecting the correct tool from several available options; formatting a function call with correctly typed arguments; handling a case where no available tool fits the request; chaining two tool calls to complete a task; correctly extracting arguments from a natural-language request
• handling a tool call that returns an error; deciding when NOT to call a tool and answer directly instead; interpreting a tool's JSON result and summarizing it for the user; handling ambiguous requests that could map to multiple tools; correctly handling optional vs required parameters
• recovering gracefully when a tool call fails; selecting between similar tools based on subtle differences; formatting a tool call for a multi-parameter search/filter function

How Rebiha prepared the training material

This page contains 994 instruction-response pairs from the existing Rebiha dataset. Its domain definition was designed around the coverage areas above so the training material spans multiple realistic tasks rather than one narrow prompt pattern.

Rebiha's broader dataset workflow uses structured quality review to help identify problems such as contradictions, unsupported claims, unsupported assumptions, calculation errors and other weak training examples. You can inspect real examples on this page before deciding whether the dataset fits your model and use case.

What is in this dataset

994 instruction-response pairs covering selecting the correct tool/function, formatting calls correctly, and handling tool results appropriately. Each pair is a realistic instruction with a full written response, in the JSONL format used for supervised fine-tuning. No synthetic filler, no duplicated rows.

Example pairs

Real rows from the dataset, shown in full.

Who this is for

Builders who want their fine-tuned model to reliably perform this specific capability, as part of a broader assistant or agent.

Which models this works with

The dataset is plain JSONL, so it works with any instruction-tuned open model. On Rebiha you can train it directly on:

• Qwen — Qwen3.8, Qwen3.6, Qwen3.5, Qwen3, Qwen2.5, Qwen2.5-Coder
• Granite — Granite 4.1 (3B, 8B, 30B)
• OLMo — OLMo 3, OLMo 3.1
• GLM — GLM-4
• Gemma, Phi, DeepSeek, Mistral, and Llama families

Training uses LoRA, or QLoRA on a 4-bit base for larger models. Your base model's weights are never modified — training produces a separate adapter.

How it works

1. Pick this dataset and a base model.
2. Rebiha runs the job on a managed GPU. You set up nothing.
3. Download your model: a ready-to-run GGUF, plus developer assets (adapter, tokenizer, configs).

Fine-tuning or RAG?

Use RAG when the model needs facts that change — your prices, your documents, today's inventory. Use fine-tuning when you want consistent behavior and structure without prompting for it every time. This dataset teaches the shape of this capability, not facts to look up.

How managed fine-tuning works

1. Inspect the dataset examples and choose a compatible base model.
2. Rebiha runs the training job on managed GPU infrastructure using LoRA or QLoRA as appropriate.
3. Download portable model assets for your own workflow, including the available ready-to-run and developer outputs for the selected training path.

Fine-tuning or RAG?

Use fine-tuning when the objective is recurring behavior: response structure, domain patterns, terminology, workflow, or how the model approaches a class of requests. Use RAG when answers depend on changing or proprietary facts that should be retrieved at request time. The two approaches can also work together.

Know what goes in. Own what comes out.

You can inspect real examples before training, choose the model you want to adapt, and keep portable model assets when training is complete.

Related datasets

• General Instruction Following — 978 pairs
• Multi-Turn Conversation — 466 pairs
• Rewriting & Editing — 854 pairs
• Summarization — 781 pairs

Start fine-tuning