Update README.md

README.md

@@ -8,18 +8,23 @@ language:
 tags:
 - completion
 ---
+# MagicPrompt TinyStories-33M (LoRA)
+
 ## Info
 
-Magic prompt completion model trained on a dataset 70k Stable Diffusion prompts. Base model: TinyStories-33M.
+Magic prompt completion model trained on a dataset 70k Stable Diffusion prompts. Base model: TinyStories-33M. Inspired by [MagicPrompt-Stable-Diffusion](https://huggingface.co/Gustavosta/MagicPrompt-Stable-Diffusion).
 
-Model seems to be pretty decent for 33M params, but it clearly lacks much of an understanding of pretty much anything. Still, considering the size, I think it's decent. Whether you would use this over a small GPT-2 based model is up to you.
+Model seems to be pretty decent for 33M params due to the TinyStories base, but it clearly lacks much of an understanding of pretty much anything. Still, considering the size, I think it's decent. Whether you would use this over a small GPT-2 based model is up to you.
 
 ## Examples
 
-Generation settings: `max_new_tokens=40, do_sample=True, temperature=2.0, num_beams=10, repetition_penalty=1.2, top_k=40, top_p=0.75, eos_token_id=tokenizer.eos_token_id` (there may be better settings).
+Best generation settings I found: `max_new_tokens=40, do_sample=True, temperature=1.2, num_beams=10, no_repeat_ngram_size=2, early_stopping=True, repetition_penalty=1.35, top_k=50, top_p=0.55, eos_token_id=tokenizer.eos_token_id, pad_token_id=0` (there may be better settings).
+`no_repeat_ngram_size` is important for making sure the model doesn't repeat phrases (as it is quite small).
 
 (Bold text is generated by the model)
 
+"found footage of a ufo **in the forest, by lusax, wlop, greg rutkowski, stanley artgerm, highly detailed, intricate, digital painting, artstation, concept art, smooth**"
+
 "A close shot of a bird in a jungle, **with two legs, with long hair on a tall, long brown body, long white skin, sharp teeth, high bones, digital painting, artstation, concept art, illustration by wlop,**"
 
 "Camera shot of **a strange young girl wearing a cloak, wearing a mask in clothes, with long curly hair, long hair, black eyes, dark skin, white teeth, long brown eyes eyes, big eyes, sharp**"
@@ -28,6 +33,12 @@ Generation settings: `max_new_tokens=40, do_sample=True, temperature=2.0, num_be
 
 "A field of flowers, camera shot, 70mm lens, **fantasy, intricate, highly detailed, artstation, concept art, sharp focus, illustration, illustration, artgerm jake daggaws, artgerm and jaggodieie brad**"
 
+## Next steps
+
+- Larger dataset ie [neuralworm/stable-diffusion-discord-prompts](https://huggingface.co/datasets/neuralworm/stable-diffusion-discord-prompts) or [daspartho/stable-diffusion-prompts](https://huggingface.co/datasets/daspartho/stable-diffusion-prompts)
+- More epochs
+- Instead of going smaller than GPT-2 137M, fine tune a 1-7B param model
+
 ## Training config
 
 - Rank 16 LoRA