seanpoyner/smolcode-coder-go-1.5b-tools

TEXT GENERATIONConcurrent Unit Cost:1Model Size:1.5BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jun 14, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The seanpoyner/smolcode-coder-go-1.5b-tools model is a 1.5 billion parameter LoRA fine-tune of Qwen2.5-Coder-1.5B-Instruct, specifically designed to enable native function call emission. This model facilitates agentic coding loops by correctly parsing tool calls, addressing a limitation in base Qwen-Coder models. With a 32768-token context length, it is optimized for driving agentic coding assistants like smolcode, particularly for small language model (SLM) applications.

Loading preview...

Overview

seanpoyner/smolcode-coder-go-1.5b-tools is a 1.5 billion parameter model, fine-tuned from Qwen2.5-Coder-1.5B-Instruct using LoRA. Its primary purpose is to enable the emission of native <tool_call> function calls, which is crucial for allowing small coder models to effectively drive agentic coding loops. This model was developed for the smolcode agentic coding assistant during the Hugging Face Build Small hackathon.

Key Capabilities

  • Native Tool Call Emission: Unlike base Qwen-Coder models that output plain-text JSON for tool calls, this fine-tune generates the native <tool_call> format, ensuring compatibility with runtimes like Ollama and llama.cpp.
  • Agentic Workflow Integration: Designed to seamlessly integrate into agentic coding workflows by providing correctly formatted tool calls.
  • Efficient Training: Utilizes bf16 LoRA with assistant-only loss, focusing on tool calls and final answers. Training data includes NousResearch/hermes-function-calling-v1 and synthetic smolcode trajectories, all rendered through the exact apply_chat_template(tools=...) used at inference.
  • High Fidelity: Version 2 (v2) specifically addresses and fixes template mismatches found in v1, ensuring that the training and inference templates are identical for robust performance.

Good For

  • Small Language Model (SLM) Agentic Coding: Ideal for scenarios where a compact, efficient model (Tiny-Titan-class) is needed to perform agentic coding tasks.
  • Tool-Use Applications: Excellent for applications requiring precise and native tool call generation for external function execution.
  • smolcode and Similar Assistants: Directly supports and enhances the functionality of smolcode and other SLM-optimized agentic coding assistants.

Finetunes
1 models