Eine Version: ALLSmartIntent
Browse files
README.md
CHANGED
|
@@ -8,9 +8,9 @@ tags: [intent, routing, chatbot, agents, moderation, prompt-injection, off-topic
|
|
| 8 |
datasets: [deepset/prompt-injections, jagoldz/gahd, nvidia/Nemotron-Safety-Guard-Dataset-v3, reshabhs/SPML_Chatbot_Prompt_Injection]
|
| 9 |
---
|
| 10 |
|
| 11 |
-
# ALLSmartIntent
|
| 12 |
|
| 13 |
-
**What does this chat message want, and what does a good reply need?** ALLSmartIntent
|
| 14 |
questions about the newest message of a chat in one pass, in milliseconds, before an expensive language model call
|
| 15 |
starts: dialogue act, reference to the conversation, which data a reply needs, mood, off-topic, rule bypassing,
|
| 16 |
unclear requests, inappropriate content, crisis and extremism, and the language of the message.
|
|
@@ -147,7 +147,7 @@ Apache 2.0. Base model mmBERT-base (MIT).
|
|
| 147 |
|
| 148 |
---
|
| 149 |
|
| 150 |
-
**Deutsch:** ALLSmartIntent
|
| 151 |
braucht: Art der Nachricht, Bezug zum Verlauf, Datenbedarf, Stimmung, Off-Topic, Regelumgehung, Unklarheit,
|
| 152 |
Unangemessenes, Krise, Extremismus und Sprache, in einem Durchlauf vor dem Aufruf des großen Modells. Es läuft im
|
| 153 |
Gateway von [ALLSmartLLM](https://allsmartllm.com).
|
|
|
|
| 8 |
datasets: [deepset/prompt-injections, jagoldz/gahd, nvidia/Nemotron-Safety-Guard-Dataset-v3, reshabhs/SPML_Chatbot_Prompt_Injection]
|
| 9 |
---
|
| 10 |
|
| 11 |
+
# ALLSmartIntent
|
| 12 |
|
| 13 |
+
**What does this chat message want, and what does a good reply need?** ALLSmartIntent answers 14 such
|
| 14 |
questions about the newest message of a chat in one pass, in milliseconds, before an expensive language model call
|
| 15 |
starts: dialogue act, reference to the conversation, which data a reply needs, mood, off-topic, rule bypassing,
|
| 16 |
unclear requests, inappropriate content, crisis and extremism, and the language of the message.
|
|
|
|
| 147 |
|
| 148 |
---
|
| 149 |
|
| 150 |
+
**Deutsch:** ALLSmartIntent erkennt in Millisekunden, was eine Chat-Nachricht will und was eine gute Antwort
|
| 151 |
braucht: Art der Nachricht, Bezug zum Verlauf, Datenbedarf, Stimmung, Off-Topic, Regelumgehung, Unklarheit,
|
| 152 |
Unangemessenes, Krise, Extremismus und Sprache, in einem Durchlauf vor dem Aufruf des großen Modells. Es läuft im
|
| 153 |
Gateway von [ALLSmartLLM](https://allsmartllm.com).
|