Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -5,14 +5,14 @@ language:
5
  pipeline_tag: text-generation
6
  library_name: transformers
7
  ---
8
- # Granite Guardian 3.1 5B
9
 
10
  ## Model Summary
11
 
12
- **Granite Guardian 3.1 5B** is a thinned down version of Granite Guardian 3.1 8B designed to detect risks in prompts and responses.
13
  It can help with risk detection along many key dimensions catalogued in the [IBM AI Risk Atlas](https://www.ibm.com/docs/en/watsonx/saas?topic=ai-risk-atlas).
14
 
15
- To generate this model, the Granite Guardian 3.1 8B is iteratively pruned and healed on the same unique data comprising human annotations and synthetic data informed by internal red-teaming used for its training. About 30% of the original parameters were removed allowing for faster inference and lower resource requirements while still providing competitive performance.
16
  It outperforms other open-source models in the same space on standard benchmarks.
17
  The thinning procedure based on iterative pruning and healing is described in more details in its own section below.
18
 
@@ -21,7 +21,7 @@ The thinning procedure based on iterative pruning and healing is described in mo
21
  - **Cookbook:** [Granite Guardian Recipes](https://github.com/ibm-granite/granite-guardian/tree/main/cookbooks/granite-guardian-3.1)
22
  - **Website**: [Granite Guardian Docs](https://www.ibm.com/granite/docs/models/guardian/)
23
  - **Paper:** [Granite Guardian](https://arxiv.org/abs/2412.07724)
24
- - **Release Date**: January 22, 2025
25
  - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
26
 
27
  ## Usage
 
5
  pipeline_tag: text-generation
6
  library_name: transformers
7
  ---
8
+ # Granite Guardian 3.2 5B
9
 
10
  ## Model Summary
11
 
12
+ **Granite Guardian 3.2 5B** is a thinned down version of Granite Guardian 3.1 8B designed to detect risks in prompts and responses.
13
  It can help with risk detection along many key dimensions catalogued in the [IBM AI Risk Atlas](https://www.ibm.com/docs/en/watsonx/saas?topic=ai-risk-atlas).
14
 
15
+ To generate this model, the Granite Guardian 3.2 8B is iteratively pruned and healed on the same unique data comprising human annotations and synthetic data informed by internal red-teaming used for its training. About 30% of the original parameters were removed allowing for faster inference and lower resource requirements while still providing competitive performance.
16
  It outperforms other open-source models in the same space on standard benchmarks.
17
  The thinning procedure based on iterative pruning and healing is described in more details in its own section below.
18
 
 
21
  - **Cookbook:** [Granite Guardian Recipes](https://github.com/ibm-granite/granite-guardian/tree/main/cookbooks/granite-guardian-3.1)
22
  - **Website**: [Granite Guardian Docs](https://www.ibm.com/granite/docs/models/guardian/)
23
  - **Paper:** [Granite Guardian](https://arxiv.org/abs/2412.07724)
24
+ - **Release Date**: Feruary 24, 2025
25
  - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
26
 
27
  ## Usage