fuzzy-mittenz commited on
Commit
f8d59a2
·
verified ·
1 Parent(s): 5bcc939

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -19,7 +19,7 @@ A low rescource frontier GitC(Guy in the Chair) model with multi-in-turn-functio
19
 
20
  ![Mjollnir.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/fjVBX5JWY8ulJrcsnMgYb.png)
21
 
22
- This is an application of a small Grok-3 style model with Multiple in turn Tool Use for edge devices. This little baby doesn't just have reasoning and tool use but multiple tool use and exceptional insight for its little size. It brings an awesome amount of functionality and usefulness to edge setups and is specifically built for the Orange pi Zero 35$ System on a board to create a flash drive functional assistant. For its size it leads the frontier.
23
 
24
  This model beats OpenAI models in Function calling in an overall score on Berkeley Function-Calling Leaderboard (BFCL-v3). It was converted using a custom importance matrix specialized for tool use in the real world. Vector smoothing and S-AGI gives this model better overall responce and assistant capabilities than any other in it's class.
25
 
 
19
 
20
  ![Mjollnir.png](https://cdn-uploads.huggingface.co/production/uploads/6593502ca2607099284523db/fjVBX5JWY8ulJrcsnMgYb.png)
21
 
22
+ This is an application of a small Effective non-reasoning tool use model with Multiple in turn Tool User for all devices. This little baby doesn't just have reasoning and tool use but multiple tool use and exceptional insight for its little size. It brings an awesome amount of functionality and usefulness to edge setups and is specifically built as a functional mobile assistant. For its size it leads the frontier.
23
 
24
  This model beats OpenAI models in Function calling in an overall score on Berkeley Function-Calling Leaderboard (BFCL-v3). It was converted using a custom importance matrix specialized for tool use in the real world. Vector smoothing and S-AGI gives this model better overall responce and assistant capabilities than any other in it's class.
25