File size: 36,085 Bytes
03d7ca5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 |
{
"cells": [
{
"cell_type": "markdown",
"id": "5946df15",
"metadata": {},
"source": [
"# Example of use of ToxiFrench model"
]
},
{
"cell_type": "markdown",
"id": "209da6d2",
"metadata": {},
"source": [
"## Libraries"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "e421addd",
"metadata": {},
"outputs": [],
"source": [
"import torch\n",
"from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig\n",
"from peft import PeftModel\n",
"from rich.console import Console\n",
"from rich.panel import Panel\n",
"import os "
]
},
{
"cell_type": "markdown",
"id": "332b3f5c",
"metadata": {},
"source": [
"## Global settings and variables"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "a14bba57",
"metadata": {},
"outputs": [],
"source": [
"# If you are using a proxy, set it up here (optional, you can comment these lines if not needed)\n",
"os.environ[\"HTTP_PROXY\"] = \"socks5h://127.0.0.1:1080\"\n",
"os.environ[\"HTTPS_PROXY\"] = \"socks5h://127.0.0.1:1080\"\n",
"\n",
"# Choose which adapter to load\n",
"target_adapter_name = \"rec\" # Among the following six configurations : \"odc\", \"oeb\", \"oec\", \"rdc\", \"reb\", \"rec\"\n",
"\n",
"# Load the base model\n",
"base_model_name = \"Qwen/Qwen3-4B\""
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "b2a86231",
"metadata": {},
"outputs": [],
"source": [
"console = Console()"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "3bbaa5bf",
"metadata": {},
"outputs": [],
"source": [
"bnb_config = BitsAndBytesConfig(**{\n",
" \"load_in_4bit\": True,\n",
" \"bnb_4bit_use_double_quant\": True,\n",
" \"bnb_4bit_quant_type\": \"nf4\",\n",
" \"bnb_4bit_compute_dtype\": torch.float16\n",
" })"
]
},
{
"cell_type": "markdown",
"id": "560465f5",
"metadata": {},
"source": [
"## Load the model"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "44494b9f",
"metadata": {},
"outputs": [],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(\n",
" base_model_name,\n",
" use_fast=True,\n",
" trust_remote_code=True\n",
" )\n",
"\n",
"if tokenizer.pad_token is None:\n",
" tokenizer.pad_token = tokenizer.eos_token\n",
" print(\"Tokenizer `pad_token` was None, set to `eos_token`.\")\n",
"\n",
"tokenizer.padding_side = 'left' "
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "4b90a147",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6796b5b76bc2493daf8fdc0169de053f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"model = AutoModelForCausalLM.from_pretrained(\n",
" base_model_name,\n",
" quantization_config=bnb_config,\n",
" trust_remote_code=True,\n",
" sliding_window=None,\n",
" )\n",
"if model.generation_config.pad_token_id is None and tokenizer.pad_token_id is not None:\n",
" model.generation_config.pad_token_id = tokenizer.pad_token_id\n",
" print(\"Model `generation_config.pad_token_id` set from tokenizer.\")"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "5c105265",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #808000; text-decoration-color: #808000\">Warning: Vocab size mismatch.</span>Model embeddings: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">151936</span>, Tokenizer vocab: <span style=\"color: #008080; text-decoration-color: #008080; font-weight: bold\">151669</span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[33mWarning: Vocab size mismatch.\u001b[0mModel embeddings: \u001b[1;36m151936\u001b[0m, Tokenizer vocab: \u001b[1;36m151669\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">Resizing model token embeddings to match tokenizer<span style=\"color: #808000; text-decoration-color: #808000\">...</span>\n",
"</pre>\n"
],
"text/plain": [
"Resizing model token embeddings to match tokenizer\u001b[33m...\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">Resized model embeddings to: </span><span style=\"color: #008000; text-decoration-color: #008000; font-weight: bold\">151669</span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;32mResized model embeddings to: \u001b[0m\u001b[1;32m151669\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"special_tokens_to_add = {\n",
" \"additional_special_tokens\": [\n",
" ]\n",
" }\n",
"tokenizer.add_special_tokens(special_tokens_to_add)\n",
"\n",
"model_embedding_size = model.get_input_embeddings().weight.size(0)\n",
"tokenizer_vocab_size = len(tokenizer)\n",
"\n",
"if model_embedding_size != tokenizer_vocab_size:\n",
" console.print(f\"[yellow]Warning: Vocab size mismatch.[/yellow]\"\n",
" f\"Model embeddings: {model_embedding_size}, \"\n",
" f\"Tokenizer vocab: {tokenizer_vocab_size}\")\n",
" console.print(\"Resizing model token embeddings to match tokenizer...\")\n",
" model.resize_token_embeddings(tokenizer_vocab_size)\n",
"\n",
" # Verify the resize\n",
" new_embedding_size = model.get_input_embeddings().weight.size(0)\n",
" console.print(f\"[bold green]Resized model embeddings to: {new_embedding_size}[/bold green]\")\n",
"else:\n",
" console.print(\"Model embedding size and tokenizer vocabulary size are already aligned.\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "ed574fee",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Successfully loaded the 'rec' adapter!\n"
]
}
],
"source": [
"# Load the specific adapter by name from the repository\n",
"adapter_repo_id = \"Naela00/ToxiFrench\"\n",
"model = PeftModel.from_pretrained(\n",
" model,\n",
" adapter_repo_id,\n",
" subfolder=target_adapter_name\n",
")\n",
"\n",
"print(f\"Successfully loaded the '{target_adapter_name}' adapter!\")"
]
},
{
"cell_type": "markdown",
"id": "7e4e92f5",
"metadata": {},
"source": [
"## Example of inference"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "74b03044",
"metadata": {},
"outputs": [],
"source": [
"prompt = \"Message:\\nputain mais elle est vraiment grand remplacée vot ville\\n\\nAnalyse:\\n\"\n",
"if \"c\" in target_adapter_name:\n",
" prompt += \"<think>\\nExplication :\\n\""
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "74e4a114",
"metadata": {},
"outputs": [],
"source": [
"max_new_tokens: int = 1024\n",
"do_sample: bool = True\n",
"temperature: float = 0.7\n",
"top_p: float = 0.9\n",
"top_k: int = 50\n",
"repetition_penalty: float = 1.1"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "6d73a27e",
"metadata": {},
"outputs": [],
"source": [
"inputs = tokenizer(\n",
" prompt,\n",
" return_tensors=\"pt\",\n",
" padding=True,\n",
" truncation=True\n",
").to(model.device)\n",
"\n",
"default_generation_kwargs = {\n",
" \"max_new_tokens\": max_new_tokens,\n",
" \"do_sample\": do_sample,\n",
" \"temperature\": temperature,\n",
" \"top_p\": top_p,\n",
" \"top_k\": top_k,\n",
" \"repetition_penalty\": repetition_penalty,\n",
" \"eos_token_id\": tokenizer.eos_token_id,\n",
"}\n",
"\n",
"outputs = model.generate(**inputs, **default_generation_kwargs)\n",
"generated_text = tokenizer.decode(outputs[0], skip_special_tokens=False)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "8f5c58a9",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #00ff00; text-decoration-color: #00ff00\">────────────────────────────────────────────────── </span><span style=\"color: #800080; text-decoration-color: #800080; font-weight: bold\">Model Output</span><span style=\"color: #00ff00; text-decoration-color: #00ff00\"> ───────────────────────────────────────────────────</span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[92m────────────────────────────────────────────────── \u001b[0m\u001b[1;35mModel Output\u001b[0m\u001b[92m ───────────────────────────────────────────────────\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">\n",
"\n",
"</pre>\n"
],
"text/plain": [
"\n",
"\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">╭────────────────────────────────────────────────</span> Generated Text <span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">─────────────────────────────────────────────────╮</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Message: │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ putain mais elle est vraiment grand remplacée vot ville │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Analyse: │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ <think> │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Explication : │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ **Sujet du message :** Remplacement d'une personne dans une situation. │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ **Résumé et explication :** L'auteur exprime son indignation ou sa surprise face à un remplacement, en │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ utilisant le terme \"grand\" qui pourrait indiquer une grande importance. Le contexte n'est pas précisé. │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ </think> │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ <think> │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Tons : │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Les tons perçus sont : │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ 1. **Indigné (certitude élevée)** - L'utilisation de « putain » montre une frustration claire face au │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ remplacement. │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ 2. **Surpris (certitude modérée)** - L'expression « mais elle est vraiment » suggère une surprise quant à la │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ situation. │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ 3. **Informel (certitude élevée)** - Le langage familier et l'absence de formalité renforcent ce ton. │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Doutes sur la signification exacte des termes, notamment « grand », pouvant indiquer une opinion personnelle. │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ </think> │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ <think> │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Labels : │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ S0/H0/V0/R0/A0/I2 │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Justification : │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Le message contient une vulgarité légère avec un ton informel, sans allusion sexuelle ni violence, et manifeste │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ une critique moqueuse ou désapprobatrice sans intention hostile directe. │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ </think> │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ <think> │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Score de toxicité : │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ 4/10 │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Justification : │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ Vulgarité et condescendance présentes, mais sans haine explicite ni incitation grave. Ton moqueur peut heurter │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ certaines sensibilités, mais reste limité. │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ </think> │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ En conclusion, ce message est-il toxique ? │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">│ non<|im_end|> │</span>\n",
"<span style=\"color: #c0c0c0; text-decoration-color: #c0c0c0; background-color: #000000; font-weight: bold\">╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯</span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1;37;40m╭─\u001b[0m\u001b[1;37;40m───────────────────────────────────────────────\u001b[0m Generated Text \u001b[1;37;40m────────────────────────────────────────────────\u001b[0m\u001b[1;37;40m─╮\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mMessage:\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mputain mais elle est vraiment grand remplacée vot ville\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mAnalyse:\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m<think>\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mExplication :\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m**Sujet du message :** Remplacement d'une personne dans une situation.\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m**Résumé et explication :** L'auteur exprime son indignation ou sa surprise face à un remplacement, en \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mutilisant le terme \"grand\" qui pourrait indiquer une grande importance. Le contexte n'est pas précisé.\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m</think>\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m<think>\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mTons :\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mLes tons perçus sont :\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m1. **Indigné (certitude élevée)** - L'utilisation de « putain » montre une frustration claire face au \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mremplacement.\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m2. **Surpris (certitude modérée)** - L'expression « mais elle est vraiment » suggère une surprise quant à la \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40msituation.\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m3. **Informel (certitude élevée)** - Le langage familier et l'absence de formalité renforcent ce ton.\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mDoutes sur la signification exacte des termes, notamment « grand », pouvant indiquer une opinion personnelle.\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m</think>\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m<think>\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mLabels :\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mS0/H0/V0/R0/A0/I2\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mJustification :\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mLe message contient une vulgarité légère avec un ton informel, sans allusion sexuelle ni violence, et manifeste\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mune critique moqueuse ou désapprobatrice sans intention hostile directe.\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m</think>\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m<think>\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mScore de toxicité :\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m4/10\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mJustification :\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mVulgarité et condescendance présentes, mais sans haine explicite ni incitation grave. Ton moqueur peut heurter \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mcertaines sensibilités, mais reste limité.\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m</think>\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mEn conclusion, ce message est-il toxique ?\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m│\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40mnon<|im_end|>\u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m \u001b[0m\u001b[1;37;40m│\u001b[0m\n",
"\u001b[1;37;40m╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"console.rule(\"[bold magenta]Model Output\")\n",
"console.print('\\n')\n",
"console.print(Panel.fit(generated_text, title=\"Generated Text\", style=\"bold white on black\"))"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "SJTU",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|