seanpoyner/smolcode-coder-git-1.5b-tools
The seanpoyner/smolcode-coder-git-1.5b-tools model is a 1.5 billion parameter LoRA fine-tune of Qwen2.5-Coder-1.5B-Instruct, developed by seanpoyner. This model is specifically trained to emit native function calls, enabling agentic coding loops for small language models. It is optimized for driving coding assistants like smolcode by correctly parsing tool-use instructions. Its primary strength lies in facilitating seamless tool integration for code generation tasks.
Loading preview...
Model Overview
seanpoyner/smolcode-coder-git-1.5b-tools is a 1.5 billion parameter LoRA fine-tune of the Qwen2.5-Coder-1.5B-Instruct base model, developed by seanpoyner. Its core purpose is to enable small coder models to effectively drive agentic coding loops by correctly emitting native <tool_call> function calls.
Key Capabilities & Differentiators
- Native Tool Call Generation: Unlike standard Qwen-Coder models that output plain-text JSON for tool calls, this fine-tune specifically generates the
<tool_call>format parsed by runtimes like Ollama and llama.cpp, crucial for agentic workflows. - Optimized for Agentic Coding: Built for the
smolcodeagentic coding assistant, it closes the gap in tool-use capabilities for tiny (≤2B) models. - Targeted Training: The model was trained using bf16 LoRA with assistant-only loss on attention and MLP projections. The training data combined
NousResearch/hermes-function-calling-v1for breadth and syntheticsmolcodetool-use trajectories for sharpness, ensuring byte-identical training and inference templates.
Use Cases
This model is ideal for developers building agentic coding assistants or applications that require small language models to interact with external tools via structured function calls. It ensures reliable tool parsing, which is critical for automated code generation and execution workflows.