pszemraj
/

opt-350m-magicprompt-SD

Text Generation

Generated from Trainer

stable diffusion

prompt engineering

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

pszemraj commited on Nov 9, 2022

Commit

7d2e4fa

•

1 Parent(s): 18099b9

Update README.md

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ widget:
  - text: "cheeps are"
    example_title: "cheeps"
 parameters:
-  min_length: 16
   max_length: 96
   no_repeat_ngram_size: 1
   do_sample: True
@@ -29,6 +29,9 @@ parameters:
 This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the Gustavosta/Stable-Diffusion-Prompts dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.2987
 ## Model description

  - text: "cheeps are"
    example_title: "cheeps"
 parameters:
+  min_length: 32
   max_length: 96
   no_repeat_ngram_size: 1
   do_sample: True
 This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the Gustavosta/Stable-Diffusion-Prompts dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.2987
+- eval_runtime            = 0:00:06.79
+- eval_steps_per_second   =     16.623
+- perplexity              =     3.6644
 ## Model description