dranger003
/

dbrx-instruct-iMat.GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

dranger003 commited on Apr 6

Commit

01aa3c8

•

1 Parent(s): d333185

Update README.md

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -19,3 +19,9 @@ base_model: databricks/dbrx-instruct
 | Layers | Context | Template |
 | --- | --- | --- |
 | <pre> </pre> | <pre>32768</pre> | <pre>\<\|im_start\|\> system<br>{system} \<\|im_end\|\><br>\<\|im_start\|\> user<br>{prompt} \<\|im_end\|\><br>\<\|im_start\|\> assistant<br> </pre> |

 | Layers | Context | Template |
 | --- | --- | --- |
 | <pre> </pre> | <pre>32768</pre> | <pre>\<\|im_start\|\> system<br>{system} \<\|im_end\|\><br>\<\|im_start\|\> user<br>{prompt} \<\|im_end\|\><br>\<\|im_start\|\> assistant<br> </pre> |
+* 16x12B MoE
+* 16 experts (12B params per single expert; top_k=4 routing)
+* 36B active params (132B total params)
+* Trained on 12T tokens
+* 32k sequence length training