| @@ -0,0 +1,81 @@ |
| 1 | +# Zed Model Improvement |
| 2 | + |
| 3 | +## Zed Assistant |
| 4 | + |
| 5 | +When using the Zed Assistant, Zed does not persistently store user content or use user content for training of its models. |
| 6 | + |
| 7 | +When using upstream services through Zed AI, we require similar assurances from our service providers. For example, usage of Anthropic Claude 3.5 via Zed AI in the Asssistant is governed by the [Anthropic Commercial Terms](https://www.anthropic.com/legal/commercial-terms) which includes the following: |
| 8 | + |
| 9 | +> "Anthropic may not train models on Customer Content from paid Services." |
| 10 | + |
| 11 | +When you directly connect the Zed Assistant with a non Zed AI service (e.g. via API key) Zed does not have access to your user content. Users should reference their agreeement with the service provider to understand what terms and conditions apply. |
| 12 | + |
| 13 | +## Zed Edit Predictions |
| 14 | + |
| 15 | +By default, when using Zed Edit Predictions, Zed does not persistently store user content or use user content for training of its models. |
| 16 | + |
| 17 | +### Opt-in |
| 18 | + |
| 19 | +Users who are working on open source licensed projects may optionally opt-in to providing model improvement feedback. This opt-in occurs on a per-project basis. If you work on multiple open source projects and wish to provide model improvement feedback you will have to opt-in for each individual project. |
| 20 | + |
| 21 | +When working on other projects where you haven't opted-in, Zed will not persistently store user content or use user content for training of its models. |
| 22 | + |
| 23 | +You can see exactly how Zed detects open source licenses in: [license_detection.rs](https://github.com/zed-industries/zed/blob/main/crates/zeta/src/license_detection.rs). |
| 24 | + |
| 25 | +### Exclusions |
| 26 | + |
| 27 | +Zed will intentionally exclude certain files from Predictive Edits entirely, even when you have opted-in to model improvement feedback. |
| 28 | + |
| 29 | +You can inspect this exclusion list by opening `zed: open default settings` from the command palette: |
| 30 | + |
| 31 | +```json |
| 32 | +{ |
| 33 | + "edit_predictions": { |
| 34 | + // A list of globs representing files that edit predictions should be disabled for. |
| 35 | + // There's a sensible default list of globs already included. |
| 36 | + // Any addition to this list will be merged with the default list. |
| 37 | + "disabled_globs": [ |
| 38 | + "**/.env*", |
| 39 | + "**/*.pem", |
| 40 | + "**/*.key", |
| 41 | + "**/*.cert", |
| 42 | + "**/*.crt", |
| 43 | + "**/secrets.yml" |
| 44 | + ] |
| 45 | + } |
| 46 | +} |
| 47 | +``` |
| 48 | + |
| 49 | +Users may explicitly exclude additional paths and/or file extensions by adding them to [`edit_predictions.disabled_globs`](https://zed.dev/docs/configuring-zed#edit-predictions) in their Zed settings.json: |
| 50 | + |
| 51 | +```json |
| 52 | +{ |
| 53 | + "edit_predictions": { |
| 54 | + "disabled_globs": ["secret_dir/*", "**/*.log"] |
| 55 | + } |
| 56 | +} |
| 57 | +``` |
| 58 | + |
| 59 | +### Data we collect |
| 60 | + |
| 61 | +For open source projects where you have opted-in, Zed may store copies of requests and responses to the Zed AI Prediction service. |
| 62 | + |
| 63 | +This data includes: |
| 64 | + |
| 65 | +- the edit prediction |
| 66 | +- a portion of the buffer content around the cursor |
| 67 | +- a few recent edits |
| 68 | +- the current buffer outline |
| 69 | +- diagnostics (errors, warnings, etc) from language servers |
| 70 | + |
| 71 | +### Data Handling |
| 72 | + |
| 73 | +Collected data is stored in Snowflake, a private database where we track other metrics. We periodically review this data to select training samples for inclusion in our model training dataset. We ensure any included data is anonymized and contains no sensitive information (access tokens, user IDs, email addresses, etc). This training dataset is publicly available at: [huggingface.co/datasets/zed-industries/zeta](https://huggingface.co/datasets/zed-industries/zeta). |
| 74 | + |
| 75 | +### Model Ouput |
| 76 | + |
| 77 | +We then use this training dataset to fine-tune [Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) and make the resulting model available here at [github.com/zed-industries/zeta](https://github.com/zed-industries/zeta) and [huggingface.co/zed-industries/zeta](https://huggingface.co/zed-industries/zeta). |
| 78 | + |
| 79 | +## Applicable terms |
| 80 | + |
| 81 | +Please see the [Zed Terms of Service](https://zed.dev/terms-of-service) for more. |