Update README.md

README.md

@@ -5,7 +5,7 @@ tags:
 datasets:
 - Gustavosta/Stable-Diffusion-Prompts
 model-index:
-- name: neo-125M-promptgen-v1-act
+- name: gpt-neo-125M-magicprompt-SD
   results: []
 widget:
  - text: "morning sun over Jakarta"
@@ -17,34 +17,27 @@ widget:
  - text: "cheeps are"
    example_title: "cheeps"
 parameters:
-  min_length: 16
+  min_length: 32
   max_length: 64
   no_repeat_ngram_size: 1
   do_sample: True
-  temperature: 1.1
-  top_k: 60
+  top_k: 50
   top_p: 0.95
-  repetition_penalty: 7.3
+  repetition_penalty: 5.5
 ---
 
-# neo-125M-promptgen-v1-act
+# gpt-neo-125M-magicprompt-SD
+
+Generate/augment your prompt, stable diffusion style.
 
 This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on the Gustavosta/Stable-Diffusion-Prompts dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.8875
 - perplexity:   6.6028
 
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
 ## Training and evaluation data
 
-More information needed
+refer to the `Gustavosta/Stable-Diffusion-Prompts` dataset.
 
 ## Training procedure