Roboshaul

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+from transformers import pipeline
+
+title = "מחולל ציטוטים פיקטיביים של שאול אמסטרדמסקי"
+description = "<p align=\"right\">✨ נונסנס כיס</p>"
+article = "<p align=\"right\">אימן: <a href=\"https://linktr.ee/Norod78\">דורון אדלר</a> באמצעות: <a href=\"https://story.kan.org.il/robo_shaul\">מאגר המידע של רובושאול</a></p>"
+model_id = "./model"
+text_generator = pipeline('text-generation', model=model_id, tokenizer=model_id)
+max_length = 128
+top_k = 40
+top_p = 0.92
+temperature = 0.98
+
+def text_generation(input_text = None):
+    if input_text == None or len(input_text) == 0:
+        input_text = ". "
+    else:   
+        input_text ="<|startoftext|>" + input_text
+    generated_text = text_generator(input_text,
+    max_length=max_length,
+    top_k=top_k, 
+    top_p=top_p,
+    temperature=temperature,
+    do_sample=True,
+    repetition_penalty=2.0,
+    num_return_sequences=1)
+    parsed_text = generated_text[0]["generated_text"].replace("<|startoftext|>", "").replace("\r","").replace("\n\n", "\n").replace("\t", " ").replace("<|pad|>", " * ").replace("\"\"", "\"")
+    return parsed_text[2:]
+gr.Interface(
+    text_generation,    
+    inputs=None,
+    outputs=gr.Textbox(lines=3, type="text", label="פה מופיע הטקסט שהמחולל יוצר, לאחר הלחיצה על הכפתור", elem_id="output_text"),
+    css="#output_text{direction: rtl} #input_text{direction: rtl}",
+    title=title,
+    description=description,
+    article=article,
+    theme="default",
+    allow_flagging="never",
+).launch()

model/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 50258,
+  "<|pad|>": 50259,
+  "<|startoftext|>": 50257
+}

model/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "Norod78/distilgpt2-base-pretrained-he",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "pad_token_id": 50257,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 50260
+}

model/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 50257,
+  "transformers_version": "4.26.1"
+}

model/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6994817063266d5f7d467ed84132e39b60714b72e8770487f177eba57b5ce21
+size 333979385

model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|endoftext|>",
+  "mask_token": "<mask>",
+  "pad_token": "<|pad|>",
+  "unk_token": "<unk>"
+}

model/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|startoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "Norod78/distilgpt2-base-pretrained-he",
+  "pad_token": "<|pad|>",
+  "special_tokens_map_file": "./distilgpt2-base-pretrained-he/special_tokens_map.json",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "unknown_token": "<|unknown|>"
+}

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+torch
+transformers
+tokenizers
+