10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 538 ms
modelrecord72 downloads/month
- text-generation
Task: text-generation
- text-generation
modelrecord780,313 downloads/month
- feature-extraction
Task: feature-extraction
- feature-extraction
modelrecord
- mistralai/mistral-7b-v0.1
A 7 billion parameter language model from Mistral.
- mistralai/mistral-7b-v0.1
modelrecord17,375 downloads/month
- image-text-to-text
Task: image-text-to-text
- image-text-to-text
modelrecord
- mistral-nemo-12b-instruct
Task: Mistral-Nemo-12B-Instruct
- mistral-nemo-12b-instruct
modelrecord
- structured-outputs
Can return JSON matching a schema.
- text->text
Takes text; returns text.
- tool-calling
Can call tools (function calling).
- structured-outputs
MCP serverrecord
- Climate_Risk_Monitoring_weather_data_forecast
7-day forecast with calibrated uncertainty bands for a location. Trains the chosen model on NASA POWER history, tests it on the last 30 days, runs a 5-fold walk-forward backtest, builds adaptive conformal intervals and compares the Winkler interval score with a seasonal-naive benchmark. Takes one to
- Climate_Risk_Monitoring_weather_data_forecast
MCP serverrecord
- timestral_5m_forecast
Zero-shot probabilistic forecast of a univariate time series with Timestral-5M. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: A pl
- timestral_5m_forecast
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.