{"id":"microsoft-sentiment-analysis-7b","slug":"microsoft-sentiment-analysis-7b","name":"Sentiment-Analysis-7B","orgId":"microsoft","family":"microsoft-sentiment-analysis-7b","releaseDate":null,"availability":"announced","openWeights":true,"license":null,"paramsTotal":7000000000,"paramsSource":"slug","contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/microsoft/Sentiment-Analysis-7B","hfRepo":null,"modalities":["text"],"aliases":["Sentiment-Analysis-7B","sentiment-analysis-7b","sentiment analysis 7b","microsoft/sentiment-analysis-7b","microsoft sentiment-analysis-7b"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-20","announced":"2026-10-20","blurb":"Microsoft's 7B open-weights model, fine-tuned from Mistral-7B-Instruct-v0.2, that labels a user message about a service, product or agent as Negative, Neutral or Positive and explains why. Trained with reinforcement learning and an LLM judge on about 300 examples without pre-defined labels. MIT license.","api":"none","openWeights":"yes","params":{"text":"7B","source":"Microsoft's Hugging Face model card (Mistral-7B-Instruct-v0.2 base)"},"facts":[{"label":"Base model","value":"mistralai/Mistral-7B-Instruct-v0.2"},{"label":"Training","value":"Reinforcement learning with an LLM as judge, on a small internal set of ~300 examples; no pre-defined labels in training"},{"label":"Output","value":"First token is the label (Negative, Neutral or Positive), followed by a short explanation"},{"label":"License","value":"MIT"},{"label":"Hugging Face repo created","value":"Oct 17, 2026 (UTC); announced Oct 20, 2026"}],"claims":["Lab claim: 72.8% accuracy on Microsoft's evaluation, against 62.0% for the Mistral-7B-Instruct-v0.2 base."],"sources":[{"kind":"repo","title":"Sentiment-Analysis-7B on Hugging Face","url":"https://huggingface.co/microsoft/Sentiment-Analysis-7B","date":"2026-10-20"},{"kind":"press","title":"HuggingPapers post on X","url":"https://x.com/HuggingPapers/status/2112629159604203995","date":"2026-10-20"}],"firstBenchmark":null},"organization":{"id":"microsoft","name":"Microsoft","slug":"microsoft","country":null,"url":null,"color":"#0078D4","mark":"MS"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Oct 20, 2026; no independent results yet.","lead":"As of Oct 22, 2026, Sentiment-Analysis-7B is pending benchmarks on isitsota: announced Oct 20, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}