libs entropy and read files

app.py

@@ -111,6 +111,7 @@ with gr.Blocks(title="Sophia, Torah Codes",css=css,js=js) as app:
 	    retry_btn=None,
 	    undo_btn="Undo",
 	    clear_btn="Clear",
+        examples=["I want you to interpret a dream where I travel to space and see the earth in small size, then a fireball comes for me and I teleport to another planet full of fruits, trees and forests, there I meet a witch who makes me drink a potion and then I wake up"]
 	)
 
     #with gr.Tab("Chat"):

lib/pipes.py

@@ -0,0 +1,102 @@
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+from diffusers import DiffusionPipeline
+from transformers import AutoModelForSeq2SeqLM
+from samplings import top_p_sampling, temperature_sampling
+import torch
+
+class AIAssistant:
+    def __init__(self):
+        pass
+
+    def entity_pos_tagger(self, example):
+        tokenizer = AutoTokenizer.from_pretrained("Davlan/bert-base-multilingual-cased-ner-hrl")
+        model = AutoModelForTokenClassification.from_pretrained("Davlan/bert-base-multilingual-cased-ner-hrl")
+        nlp = pipeline("ner", model=model, tokenizer=tokenizer)
+        ner_results = nlp(example)
+        return ner_results
+
+    def text_to_image_generation(self, prompt, n_steps=40, high_noise_frac=0.8):
+        base = DiffusionPipeline.from_pretrained(
+            "stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16, variant="fp16", use_safetensors=True
+        )
+        base.to("cuda")
+        refiner = DiffusionPipeline.from_pretrained(
+            "stabilityai/stable-diffusion-xl-refiner-1.0",
+            text_encoder_2=base.text_encoder_2,
+            vae=base.vae,
+            torch_dtype=torch.float16,
+            use_safetensors=True,
+            variant="fp16",
+        )
+        refiner.to("cuda")
+
+        image = base(
+            prompt=prompt,
+            num_inference_steps=n_steps,
+            denoising_end=high_noise_frac,
+            output_type="latent",
+        ).images
+        image = refiner(
+            prompt=prompt,
+            num_inference_steps=n_steps,
+            denoising_start=high_noise_frac,
+            image=image,
+        ).images[0]
+        return image
+
+    def grammatical_pos_tagger(self, text):
+        nlp_pos = pipeline(
+            "ner",
+            model="mrm8488/bert-spanish-cased-finetuned-pos",
+            tokenizer=(
+                'mrm8488/bert-spanish-cased-finetuned-pos',
+                {"use_fast": False}
+        ))
+        return nlp_pos(text)
+
+    def text_to_music(self, text, max_length=1024, top_p=0.9, temperature=1.0):
+        tokenizer = AutoTokenizer.from_pretrained('sander-wood/text-to-music')
+        model = AutoModelForSeq2SeqLM.from_pretrained('sander-wood/text-to-music')
+
+        input_ids = tokenizer(text,
+                              return_tensors='pt',
+                              truncation=True,
+                              max_length=max_length)['input_ids']
+
+        decoder_start_token_id = model.config.decoder_start_token_id
+        eos_token_id = model.config.eos_token_id
+
+        decoder_input_ids = torch.tensor([[decoder_start_token_id]])
+
+        for t_idx in range(max_length):
+            outputs = model(input_ids=input_ids,
+                            decoder_input_ids=decoder_input_ids)
+            probs = outputs.logits[0][-1]
+            probs = torch.nn.Softmax(dim=-1)(probs).detach().numpy()
+            sampled_id = temperature_sampling(probs=top_p_sampling(probs,
+                                                                top_p=top_p,
+                                                                return_probs=True),
+                                            temperature=temperature)
+            decoder_input_ids = torch.cat((decoder_input_ids, torch.tensor([[sampled_id]])), 1)
+            if sampled_id!=eos_token_id:
+                continue
+            else:
+                tune = "X:1\n"
+                tune += tokenizer.decode(decoder_input_ids[0], skip_special_tokens=True)
+                return tune
+                break
+
+# Ejemplo de uso
+assistant = AIAssistant()
+ner_results = assistant.entity_pos_tagger("Nader Jokhadar had given Syria the lead with a well-struck header in the seventh minute.")
+print(ner_results)
+
+image = assistant.text_to_image_generation("A majestic lion jumping from a big stone at night")
+print(image)
+
+pos_tags = assistant.grammatical_pos_tagger('Mis amigos están pensando en viajar a Londres este verano')
+print(pos_tags)
+
+tune = assistant.text_to_music("This is a traditional Irish dance music.")
+print(tune)
+