nacer0 commited on
Commit
d79ef1b
·
verified ·
1 Parent(s): c7c0881

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -6
README.md CHANGED
@@ -6,16 +6,20 @@ tags:
6
  - policy_compliance
7
  - factchecking
8
  - instruction_following
 
 
 
 
9
  base_model:
10
  - akjindal53244/Llama-3.1-Storm-8B
11
  ---
12
 
13
- # NAVI verifiers (Nace Automated Verification Intelligence)
14
 
15
- NAVI (Nace Automated Verification Intelligence) is a solution for policy alignment verification designed to review various types of text against documents and policies, and identify violating content. It is specifically optimized for enterprise applications requiring compliance verification for automated text generation. To push policy verification in the open-source community, we release NAVI-small-preview, an open-weights version of the model we have deployed on the platform. NAVI-small-preview is centered around verifying specifically assitant outputs against some policy documents. The full solution is available through [NAVI platform and API](https://naviml.com/).
16
 
17
  - **Developed by:** Nace.AI
18
- - **Model type:** Policy Alignment Verifier
19
  - **Language(s) (NLP):** English
20
  - **License:** MIT
21
  - **Finetuned from model:** akjindal53244/Llama-3.1-Storm-8B
@@ -24,11 +28,11 @@ NAVI (Nace Automated Verification Intelligence) is a solution for policy alignme
24
 
25
  ### Direct Use
26
 
27
- NAVI-small-preview is used for verifying compliance of assistant outputs with enterprise policy documents. It processes policies and identifies any contradictions, inconsistencies and violations.
28
 
29
  ### Downstream Use
30
 
31
- May be integrated into enterprise-level AI systems to automate compliance checks in diverse industries such as legal, finance, and retail.
32
 
33
  ### Out-of-Scope Use
34
 
@@ -142,4 +146,4 @@ NAVI-small-preview achieved an F1 score of 86.8% on public subset of PAV dataset
142
 
143
  ## Model Card Contact
144
 
145
- [NAVI Contact Page](https://naviml.com/contact)
 
6
  - policy_compliance
7
  - factchecking
8
  - instruction_following
9
+ - safeguards
10
+ - guardrail
11
+ - guard
12
+ - hallucination
13
  base_model:
14
  - akjindal53244/Llama-3.1-Storm-8B
15
  ---
16
 
17
+ # NAVI verifiers (Nace Verification Intelligence)
18
 
19
+ NAVI (Nace Verification Intelligence) is a hallucination detection safety model primarily for policy alignment verifications. It is designed to review various types of text against documents and policies, and identify violating content. It is specifically optimized for enterprise applications requiring compliance verification for automated text generation. To push policy verification in the open-source community, we release NAVI-small-preview, an open-weights version of the model we have deployed on the platform. NAVI-small-preview is centered around verifying specifically assitant outputs against some policy documents. The full solution is available through [NAVI platform and API](https://naviml.com/).
20
 
21
  - **Developed by:** Nace.AI
22
+ - **Model type:** Safety model, Policy Alignment Verifier
23
  - **Language(s) (NLP):** English
24
  - **License:** MIT
25
  - **Finetuned from model:** akjindal53244/Llama-3.1-Storm-8B
 
28
 
29
  ### Direct Use
30
 
31
+ NAVI-small-preview is used for verifying chatbot/assistant/agents outputs with company policy documents. It processes policies and identifies any contradictions, inconsistencies and violations.
32
 
33
  ### Downstream Use
34
 
35
+ Policy checks for accuracy critical LLM Apps. Good suite for Enterprise Environment.
36
 
37
  ### Out-of-Scope Use
38
 
 
146
 
147
  ## Model Card Contact
148
 
149
+ [NAVI Contact Page](https://naviml.com/contact)