BEE-spoke-data
/

smol_llama-220M-openhermes

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

pszemraj commited on Jan 3

Commit

356848c

•

1 Parent(s): 364d895

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -12,9 +12,9 @@ inference:
     top_k: 50
     min_new_tokens: 2
     max_new_tokens: 96
-    repetition_penalty: 1.01
     no_repeat_ngram_size: 5
-    epsilon_cutoff: 0.0006
 widget:
   - text: >
       Below is an instruction that describes a task, paired with an input that
@@ -74,9 +74,9 @@ inference:
     top_k: 50
     min_new_tokens: 2
     max_new_tokens: 96
-    repetition_penalty: 1.01
     no_repeat_ngram_size: 5
-    epsilon_cutoff: 0.0006
 ```
 Feel free to experiment with the parameters using the model in Python and let us know if you have improved results with other params!

     top_k: 50
     min_new_tokens: 2
     max_new_tokens: 96
+    repetition_penalty: 1.03
     no_repeat_ngram_size: 5
+    epsilon_cutoff: 0.0008
 widget:
   - text: >
       Below is an instruction that describes a task, paired with an input that
     top_k: 50
     min_new_tokens: 2
     max_new_tokens: 96
+    repetition_penalty: 1.03
     no_repeat_ngram_size: 5
+    epsilon_cutoff: 0.0008
 ```
 Feel free to experiment with the parameters using the model in Python and let us know if you have improved results with other params!