Firefly-v5-agentic-multiharness
a multi-harness agentic model for coding
1 min read
This model is an adapter based on Guilherme34/Firefly-v5, turned into a full-fledged multi-harness agentic model for writing code and tool-calling. Training was carried out using Easy-Agenticify via corrective SFT (supervised fine-tuning) and Posterior-GRPO RL. It supports a wide range of popular development environments and clients, ensuring seamless integration into familiar workflows.
Key features
- Support for multiple harnesses: pi, claude-code, opencode, codex, hermes, mini-swe-agent, aider, terminus-2, openhands, kimi-cli, goose.
- Built-in thinking mode (enable_thinking), enabled by default.
- Complete elimination of critical defects in tool-calling and coding after multi-stage training.
- Use of an orthogonal LoRA Super-Adapter (rank=352, combination_type="cat") with low subspace cosine similarity.
What you can do
- Run a local server via vLLM to serve autocomplete and test-fixing agents.
- Connect the model to CLI utilities like Aider or Claude Code via an environment variable for code debugging.
- Use it in open development environments to automate programming tasks.
Example
vllm serve Guilherme34/Firefly-v5-agentic-multiharness \
--return-tokens-as-token-ids \
--logprobs-mode processed_logprobs \
--enable-auto-tool-choiceRead more
DetailsBase model: Guilherme34/Firefly-v5
Export mode: super_adapter
Secondary diagonal mean cosine similarity: 0.011
Datasets: SmolDataEnvs-harbor-train, SmolDataEnvs-multiharness-sft










Comments