初始化项目，由ModelHub XC社区提供模型

Model: Karlzhy/Content_Review_Model
Source: Original Platform

.gitattributes

@@ -0,0 +1,47 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

1.py

@@ -0,0 +1,24 @@
+import json
+import random
+from datasets import Dataset, DatasetDict
+from sklearn.model_selection import train_test_split
+
+# ✅ 加载 train.jsonl
+with open("train.jsonl", "r", encoding="utf-8") as f:
+    samples = [json.loads(line.strip()) for line in f]
+
+print(f"总样本数: {len(samples)}")
+
+# ✅ 随机划分为训练集 / 验证集
+train_data, val_data = train_test_split(samples, test_size=0.1, random_state=42)
+
+# ✅ 转换为 HF Dataset
+dataset = DatasetDict({
+    "train": Dataset.from_list(train_data),
+    "validation": Dataset.from_list(val_data)
+})
+
+# ✅ 保存到磁盘（可选）
+dataset.save_to_disk("qwen_classification_dataset")
+
+print("✅ 已保存 HuggingFace Dataset 到 ./qwen_classification_dataset")

2.py

@@ -0,0 +1,110 @@
+import os
+import torch
+import inspect
+from datasets import load_from_disk
+from transformers import (
+    AutoTokenizer,
+    AutoModelForSequenceClassification,
+    TrainingArguments,
+    Trainer
+)
+from peft import LoraConfig, get_peft_model, TaskType
+from sklearn.metrics import accuracy_score, f1_score
+
+# ✅ Hugging Face Token
+hf_token = "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"
+
+# ✅ 检查 TrainingArguments 来源
+from transformers import TrainingArguments
+print("🧠 当前 TrainingArguments 来源:", inspect.getfile(TrainingArguments))
+
+# ✅ 模型与 LoRA 配置
+base_model = "Qwen/Qwen2-0.5B-Instruct"
+output_dir = "./qwen_lora_checkpoint"
+
+lora_config = LoraConfig(
+    r=8,
+    lora_alpha=16,
+    lora_dropout=0.05,
+    bias="none",
+    task_type=TaskType.SEQ_CLS,
+    target_modules=["q_proj", "v_proj"]
+)
+
+# ✅ 加载 tokenizer，并设置 pad_token
+tokenizer = AutoTokenizer.from_pretrained(
+    base_model,
+    token=hf_token,
+    trust_remote_code=True
+)
+tokenizer.pad_token = tokenizer.eos_token
+pad_token_id = tokenizer.pad_token_id
+
+# ✅ 加载模型（只加载一次），并设置 pad_token_id
+base = AutoModelForSequenceClassification.from_pretrained(
+    base_model,
+    token=hf_token,
+    trust_remote_code=True,
+    num_labels=2
+)
+base.config.pad_token_id = pad_token_id
+
+# ✅ 应用 LoRA
+model = get_peft_model(base, lora_config)
+
+# ✅ 加载数据
+dataset = load_from_disk("./qwen_classification_dataset")
+
+def preprocess(example):
+    return tokenizer(example["text"], truncation=True, padding="max_length", max_length=512)
+
+tokenized_dataset = dataset.map(preprocess, batched=True)
+tokenized_dataset = tokenized_dataset.rename_column("label", "labels")
+tokenized_dataset.set_format(type="torch", columns=["input_ids", "attention_mask", "labels"])
+
+# ✅ 训练参数（自动使用 GPU / fp16）
+training_args = TrainingArguments(
+    output_dir=output_dir,
+    per_device_train_batch_size=8,
+    per_device_eval_batch_size=8,
+    learning_rate=2e-5,
+    num_train_epochs=3,
+    evaluation_strategy="epoch",
+    save_strategy="epoch",
+    logging_dir=f"{output_dir}/logs",
+    save_total_limit=2,
+    load_best_model_at_end=True,
+    metric_for_best_model="accuracy",
+    remove_unused_columns=False,
+    report_to="none",
+    fp16=torch.cuda.is_available(),  # 自动开启 fp16
+    gradient_accumulation_steps=2,
+    dataloader_pin_memory=True,
+)
+
+# ✅ 评估函数
+def compute_metrics(eval_pred):
+    logits, labels = eval_pred
+    preds = torch.argmax(torch.tensor(logits), dim=1)
+    acc = accuracy_score(labels, preds)
+    f1 = f1_score(labels, preds)
+    return {"accuracy": acc, "f1": f1}
+
+# ✅ 构建 Trainer
+trainer = Trainer(
+    model=model,
+    tokenizer=tokenizer,
+    args=training_args,
+    train_dataset=tokenized_dataset["train"],
+    eval_dataset=tokenized_dataset["validation"],
+    compute_metrics=compute_metrics,
+)
+
+# ✅ 开始训练
+trainer.train()
+
+# ✅ 保存模型和 tokenizer
+model.save_pretrained(output_dir)
+tokenizer.save_pretrained(output_dir)
+
+print(f"✅ 微调完成，模型保存在 {output_dir}")

README.md

@@ -0,0 +1,51 @@
+---
+frameworks:
+- Pytorch
+license: Apache License 2.0
+tasks:
+- text-generation
+
+#model-type:
+##如 gpt、phi、llama、chatglm、baichuan 等
+#- gpt
+
+#domain:
+##如 nlp、cv、audio、multi-modal
+#- nlp
+
+#language:
+##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
+#- cn 
+
+#metrics:
+##如 CIDEr、Blue、ROUGE 等
+#- CIDEr
+
+#tags:
+##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
+#- pretrained
+
+#tools:
+##如 vllm、fastchat、llamacpp、AdaSeq 等
+#- vllm
+---
+### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
+#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
+
+SDK下载
+```bash
+#安装ModelScope
+pip install modelscope
+```
+```python
+#SDK模型下载
+from modelscope import snapshot_download
+model_dir = snapshot_download('Karlzhy/Content_Review_Model')
+```
+Git下载
+```
+#Git模型下载
+git clone https://www.modelscope.cn/Karlzhy/Content_Review_Model.git
+```
+
+<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.40.1"
+}

m2.py

@@ -0,0 +1,22 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel, PeftConfig
+
+peft_path = "./qwen_lora_checkpoint"
+merged_path = "./qwen2_ad_audit_merged"
+
+# 读取 LoRA 配置
+config = PeftConfig.from_pretrained(peft_path)
+
+# 加载 base 模型
+base = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, trust_remote_code=True)
+
+# 注入 LoRA
+model = PeftModel.from_pretrained(base, peft_path)
+
+# 合并
+model = model.merge_and_unload()
+
+# 保存合并后的完整模型
+model.save_pretrained(merged_path)
+tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path, trust_remote_code=True)
+tokenizer.save_pretrained(merged_path)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71f4dc5a0a1da89fbfe62b9187ece8b9b142be679a23409b0fc91440a21e81a
+size 1976163472

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}