Lfm2.5 Audio Tool Aware v4

--- license: other license_name: lfm-open-license-v1.0 license_link: LICENSE base_model: LiquidAI/LFM2.5-Audio-1.5B tags: - audio - speech-to-speech - lfm2-audio - voice-assistant - tool-use - tool-aware - context-narration language: - en datasets: - matbee/lfm2-tool-aware-dataset-v4 library_name: liquid_audio pipeline_tag: audio-to-audio --- # LFM2.5-Audio-1.5B — Tool-Aware Fine-Tune (v4) Full fine-tune of [`LiquidAI/LFM2.5-Audio-1.5B`](https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B) that handles both turns of a tool-augmented voice flow plus chitchat and refusals. | Class | Trigger | Behavior | |---|---|---| | `tool_match` | user audio + `Tools available:` block, requested tool listed | Short ack (`"setting your alarm now."`) then stop | | `tool_result_speak` | same audio + `Known facts you must use…` block injected via `set_context()` | Speak the result naturally (`"your alarm is set for 7am."`) | | `tool_miss` | requested tool not in the listed set | Polite refusal (`"i don't have a maps tool right now, sorry."`) | | `non_tool` | conversational query, no tool implied | Base-model-style natural reply (targets self-distilled from base) | ## Results vs v3 Held-out eval, 120 rows × 30 per class: | Class | v3 | **v4** | Δ | |---|---|---|---| | `tool_match` | 96.7% | 86.7% | −10.0 | | `tool_result_speak` | 100.0% | **100.0%** | 0 | | `tool_miss` | 80.0% | **100.0%** | **+20.0** | | `non_tool` | 60.0% | **86.7%** | **+26.7** | | **Overall** | **84.0%** | **93.3%** | **+9.3** | **Novel-facts narration** (60 OOD tool results never in training): **95% faithful / 0% memorized**. ## What changed in v4 1. **`tool_miss` ratio bumped** 14% → 28%. 2. **Hard-negative `tools_listed`**: 60% of `tool_miss` rows include a *semantically adjacent* tool (e.g. scenario=traffic with `maps` listed but not `traffic`). 3. **19 diversified refusal templates** (v3 had 5; v3 memorized phrasings). 4. **Explicit "if not listed, decline" clause** in the instruction line. 5. **Tighter `non_tool` filter** — drops DailyDialog context-fragments (`"Spring ."`, `"About 6:00 ."`). ## Two-turn flow ```python # turn 1 — model emits "let me check the weather." and stops # coordinator runs the weather tool, gets "Weather in Tokyo: 72°F, sunny." await ctrl.<audio_node>.set_context("Weather in Tokyo: 72°F, sunny.") # turn 2 — re-feed same user audio; model narrates ("it's 72...