Tool use and agents · Watt AI
watt-tool 8B
Llama 3.1 8B tune for multi-turn tool use.
Datasheet
Maker | Watt AI |
|---|---|
Parameters | 8.03 BVerifiedsafetensors.total from the HF API Source |
Licence | Apache-2.0Verified |
Access | Public download |
Task (HF pipeline) | — |
First published on HF | 2024-12-19 |
Last updated on HF | 2024-12-20 |
Weights in memory | 16 GB at 16-bit · 4.9 GB at ~4.85 bitsEstimateParameters × bits ÷ 8. Excludes context cache and runtime overhead; not every model has a 4-bit build. |
Benchmark
Not yet measured
BFCL V4, overall accuracy
No comparable public score for this benchmark yet. We will not estimate one.
The description summarises the model card at https://huggingface.co/watt-ai/watt-tool-8B. Parameters and licence are read from the Hugging Face API; the weights-in-memory line is our arithmetic, not a measurement.