tljohnsilver commited on
Commit
96fd4e3
·
verified ·
1 Parent(s): 992d395

Model card: Galvanize 3 runs the zn cloud check since 23 October 2026

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -24,7 +24,7 @@ tags:
24
 
25
  > **Update (October 2026).** The public benchmark result on this card was decontaminated against the training data of Galvanize 2, not against the data Galvanize-60M was trained on. Some of those sets, in particular the deepset prompt-injections and jackhhao jailbreak-classification test sets, very likely overlap with this model's training data, so its scores there, and the macro average that includes them, probably overstate how it does on new data. The corrected sentence is in "Public benchmark" below. We will publish comparable results when anyone can reproduce them. This card also no longer quotes results on attacks from our internal red-team tooling: those attacks are private, so the figures could not be checked or reproduced. The held-out results below were measured on a set that also contains such attacks; they are kept as published.
26
 
27
- > Galvanize 2 replaces this model in the zn cloud check since 12 October 2026: https://huggingface.co/usezn/Galvanize-2 . Galvanize-60M remains available and is used as an automatic fallback.
28
 
29
  Galvanize-60M is a small binary classifier that scores a piece of untrusted text (a user message, a web page, a file or a tool result) for prompt injection before it reaches an AI agent. It was the detector of the usezn.com API until 12 October 2026 and is now its automatic fallback. [zn-gate](https://github.com/usezn/zn) does not run it on your machine: see "Use with agents".
30
 
@@ -147,7 +147,7 @@ model.load_state_dict(load_file(hf_hub_download("usezn/Galvanize-60M", "model.sa
147
 
148
  `npx -y zn-gate mcp` runs zn-gate as a local MCP server. zn-gate (1.4.1 and later) does not run this model on your machine: its local checks are a deterministic rules engine and secret redaction, and tool output, tool-call arguments and MCP tool descriptions are never sent anywhere.
149
 
150
- zn-gate has an optional cloud check for prompts (`analyze_prompt`, `zn-gate analyze`, Python `analyze()`). It is off by default and runs only if you set both `ZN_CLOUD=1` and `ZN_API_KEY`. The secrets zn-gate detects are removed from the prompt on your machine before it is sent; personal data is not removed on this path. `ZN_LOCAL_ONLY=true` overrides `ZN_CLOUD=1`. Since 12 October 2026 this cloud check runs Galvanize 2, with Galvanize-60M as an automatic fallback. See [github.com/usezn/zn](https://github.com/usezn/zn).
151
 
152
  ## Citation
153
 
 
24
 
25
  > **Update (October 2026).** The public benchmark result on this card was decontaminated against the training data of Galvanize 2, not against the data Galvanize-60M was trained on. Some of those sets, in particular the deepset prompt-injections and jackhhao jailbreak-classification test sets, very likely overlap with this model's training data, so its scores there, and the macro average that includes them, probably overstate how it does on new data. The corrected sentence is in "Public benchmark" below. We will publish comparable results when anyone can reproduce them. This card also no longer quotes results on attacks from our internal red-team tooling: those attacks are private, so the figures could not be checked or reproduced. The held-out results below were measured on a set that also contains such attacks; they are kept as published.
26
 
27
+ > Galvanize 2 replaced this model in the zn cloud check on 12 October 2026 (https://huggingface.co/usezn/Galvanize-2), and Galvanize 3 replaced Galvanize 2 on 23 October 2026: https://huggingface.co/usezn/Galvanize-3 . Galvanize-60M remains available and is used as an automatic fallback.
28
 
29
  Galvanize-60M is a small binary classifier that scores a piece of untrusted text (a user message, a web page, a file or a tool result) for prompt injection before it reaches an AI agent. It was the detector of the usezn.com API until 12 October 2026 and is now its automatic fallback. [zn-gate](https://github.com/usezn/zn) does not run it on your machine: see "Use with agents".
30
 
 
147
 
148
  `npx -y zn-gate mcp` runs zn-gate as a local MCP server. zn-gate (1.4.1 and later) does not run this model on your machine: its local checks are a deterministic rules engine and secret redaction, and tool output, tool-call arguments and MCP tool descriptions are never sent anywhere.
149
 
150
+ zn-gate has an optional cloud check for prompts (`analyze_prompt`, `zn-gate analyze`, Python `analyze()`). It is off by default and runs only if you set both `ZN_CLOUD=1` and `ZN_API_KEY`. The secrets zn-gate detects are removed from the prompt on your machine before it is sent; personal data is not removed on this path. `ZN_LOCAL_ONLY=true` overrides `ZN_CLOUD=1`. Since 23 October 2026 this cloud check runs Galvanize 3 (Galvanize 2 from 12 to 23 October 2026), with Galvanize-60M as an automatic fallback. See [github.com/usezn/zn](https://github.com/usezn/zn).
151
 
152
  ## Citation
153