Update model

README.md

@@ -1,3 +1,25 @@
----
-license: mit
----
+# MagicPrompt - Stable Diffusion
+
+This is a model from the MagicPrompt series of models, which are [GPT-2](https://huggingface.co/gpt2) models intended to generate prompt texts for imaging AIs, in this case: [Stable Diffusion](https://huggingface.co/CompVis/stable-diffusion).
+
+## 🖼️ Here's an example:
+
+<img src="https://files.catbox.moe/ac3jq7.png">
+
+This model was trained with 150,000 steps and a set of about 80,000 data filtered and extracted from the image finder for Stable Diffusion: "[Lexica.art](https://lexica.art/)". It was a little difficult to extract the data, since the search engine still doesn't have a public API without being protected by cloudflare, but if you want to take a look at the original dataset, you can have a look here: [Gustavosta/MagicPrompt-Dalle](https://huggingface.co/Gustavosta/MagicPrompt-Dalle).
+
+If you want to test the model with a demo, you can go to: "[Gustavosta/spaces/MagicPrompt-Dalle](https://huggingface.co/Gustavosta/spaces/MagicPrompt-Stable_diffusion)".
+
+## 💻 You can see other MagicPrompt models:
+
+- For Dall-E 2: [Gustavosta/MagicPrompt-Dalle](https://huggingface.co/Gustavosta/MagicPrompt-Dalle)
+- For Midjourney: [Gustavosta/MagicPrompt-Midourney](https://huggingface.co/Gustavosta/MagicPrompt-Midjourney)
+- MagicPrompt full: [Gustavosta/MagicPrompt](https://huggingface.co/Gustavosta/MagicPrompt)
+
+## ⚖️ Licence:
+
+[MIT](https://huggingface.co/models?license=license:mit)
+
+When using this model, please credit: [Gustavosta](https://huggingface.co/Gustavosta)
+
+**Thanks for reading this far! :)**

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2-medium",
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,13 +12,11 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 24,
+  "n_layer": 12,
   "n_positions": 1024,
-  "n_special": 0,
-  "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0798154f31c6204bdcd13e9a1852335207cba11624d57c346aaff358fcc317d6
-size 1444566873
+oid sha256:749116704f061992e879013cb4433f9e093f385dd5a807b20ac7d226c5f53926
+size 510396521

tokenizer_config.json

@@ -3,7 +3,7 @@
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
-  "name_or_path": "gpt2-medium",
+  "name_or_path": "gpt2",
   "special_tokens_map_file": null,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c9cbb0e886fec856200e407be281337a89e1673ff724aa10d72e571f508489e
+oid sha256:f8d232c6d8bad47a89e6e1288360216bdb7652ddaa31c885db847aa20b29fd85
 size 3375