Generative AI (GenAI): Difference between revisions
Jump to navigation
Jump to search
No edit summary |
No edit summary |
||
| (26 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
Generative AI [[Neural Network]] models are used in multiple ways in the {{software}} by [[AI Agent]]s. | |||
===Large Language Models=== | |||
List of open weight Large Language Models (LLM){{ref|LLM}} models available to Chat Agents. | |||
* '''Gemma4 (Speed)''': Gemma4 model{{ref|Gemma4}} optimized for fast reactions. | |||
* '''Qwen3.8 (Quality)''': Qwen3.8 model{{ref|Qwen3.8}} optimized for quality needed for coding, creating [[TQL]] queries and calling session endpoints. | |||
===Vision Models=== | |||
These models help the LLM's to identify features in images from the interface or e.g. Overlay exports. | |||
===Diffusion Models=== | |||
These models can create new or edit existing images that can be used in Design Agents. | |||
* '''Qwen-Image 2511''': Qwen Image model{{ref|QwenImage}}. | |||
===Embeddings=== | |||
Embedding model used for AI assisted data search. | |||
* '''Embeddinggemma''': Embedding Gemma{{ref|EmbeddingGemma}} Fast embedding model. | |||
{{article end | {{article end | ||
|notes= | |notes= | ||
* | * All models run Tygron [[Cloud Computing]] servers, with no links to external hosting and follow strict [[AI Rules]]. | ||
* | |seealso=*[[Chat Channel]] | ||
*[[AI Agent]] | |||
|references= | |references= | ||
<references> | <references> | ||
| Line 25: | Line 40: | ||
|lastvisit=2026-06-29 | |lastvisit=2026-06-29 | ||
}} | }} | ||
{{ref| | {{ref|EmbeddingGemma | ||
|name= | |name=Embedding Gemma | ||
|author= | |author= | ||
|page= | |page= | ||
|source= | |source= | ||
|link=https:// | |link=https://deepmind.google/models/gemma/embeddinggemma/ | ||
|lastvisit=2026- | |lastvisit=2026-10-07 | ||
}} | |||
{{ref|Qwen3.8 | |||
|name=Qwen3.8 | |||
|author= | |||
|page= | |||
|source= | |||
|link=https://qwen.ai/ | |||
|lastvisit=2026-09-03 | |||
}} | }} | ||
{{ref| | {{ref|QwenImage | ||
|name= | |name=Qwen Image 2511 | ||
|author= | |author= | ||
|page= | |page= | ||
|source= | |source= | ||
|link=https:// | |link=https://github.com/QwenLM/Qwen-Image | ||
|lastvisit=2026- | |lastvisit=2026-10-03 | ||
}} | }} | ||
</references> | </references> | ||
|howtos=*[[How to change the LLM of a Chat Channel]] | |||
|api=* [[Api session event editor chat set neural network]] | |||
}} | }} | ||
{{Editor community nav}} | |||
Latest revision as of 14:45, 7 October 2026
Generative AI Neural Network models are used in multiple ways in the Tygron Platform by AI Agents.
Large Language Models
List of open weight Large Language Models (LLM)[1] models available to Chat Agents.
- Gemma4 (Speed): Gemma4 model[2] optimized for fast reactions.
- Qwen3.8 (Quality): Qwen3.8 model[3] optimized for quality needed for coding, creating TQL queries and calling session endpoints.
Vision Models
These models help the LLM's to identify features in images from the interface or e.g. Overlay exports.
Diffusion Models
These models can create new or edit existing images that can be used in Design Agents.
- Qwen-Image 2511: Qwen Image model[4].
Embeddings
Embedding model used for AI assisted data search.
- Embeddinggemma: Embedding Gemma[5] Fast embedding model.
Notes
- All models run Tygron Cloud Computing servers, with no links to external hosting and follow strict AI Rules.
How-to's
See also
API Endpoints
References
- ↑ LLM ∙ Found at: https://en.wikipedia.org/wiki/Large_language_model ∙ (last visited: 2026-06-29)
- ↑ Gemma4 ∙ Found at: https://deepmind.google/models/gemma/gemma-4/ ∙ (last visited: 2026-06-29)
- ↑ Qwen3.8 ∙ Found at: https://qwen.ai/ ∙ (last visited: 2026-09-03)
- ↑ Qwen Image 2511 ∙ Found at: https://github.com/QwenLM/Qwen-Image ∙ (last visited: 2026-10-03)
- ↑ Embedding Gemma ∙ Found at: https://deepmind.google/models/gemma/embeddinggemma/ ∙ (last visited: 2026-10-07)