seanpoyner/smolcode-coder-java-1.5b-tools
The seanpoyner/smolcode-coder-java-1.5b-tools model is a 1.5 billion parameter LoRA fine-tune of Qwen2.5-Coder-1.5B-Instruct, developed by seanpoyner. It specializes in emitting native function calls, enabling agentic coding loops for small language models. This model is optimized for tool-use scenarios, specifically designed to drive agentic coding assistants like smolcode.
Loading preview...
Model Overview
This model, smolcode-coder-java-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 primary purpose is to enable small language models (SLMs) to perform agentic coding by emitting native <tool_call> function calls, which are directly parseable by runtimes like Ollama and llama.cpp. This addresses a limitation in standard Qwen-Coder models that typically describe tool calls as plain-text JSON, breaking agentic tool-use loops.
Key Capabilities
- Native Tool Call Emission: Generates
<tool_call>{"name": ..., "arguments": ...}</tool_call>format, crucial for agentic workflows. - Optimized for Agentic Coding: Specifically designed to drive agentic coding assistants, such as
smolcode. - Efficient Fine-tuning: Utilizes bf16 LoRA with assistant-only loss, focusing training on tool calls and final answers.
- Context-Aware Training: Trained on
NousResearch/hermes-function-calling-v1and syntheticsmolcodetool-use trajectories, ensuring byte-identical training targets to inference prompts.
Good For
- Developers building agentic coding assistants that require precise tool-use capabilities from small models.
- Scenarios where efficient, parseable tool calls are critical for integrating LLMs with external functions or APIs.
- Projects leveraging Qwen2.5-Coder-1.5B-Instruct and needing enhanced function-calling reliability.