add v5

LLM-Detector-V5-11w/README.md

@@ -0,0 +1,56 @@
+---
+license: other
+base_model: ./Qwen-14B-Chat
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen-14b
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen-14b
+
+This model is a fine-tuned version of [./Qwen-14B-Chat](https://huggingface.co/./Qwen-14B-Chat) on the ta, the tb, the tc, the td, the te, the tf, the tg and the th datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.33.0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.7
+- Tokenizers 0.13.3

LLM-Detector-V5-11w/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Qwen-14B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V5-11w/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde59642634b55ccc32fb6fa05297f77f206ce08fa02e68f91dea53f86214102
+size 26243102

LLM-Detector-V5-11w/all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.018557672745323963,
+    "train_runtime": 121687.4213,
+    "train_samples_per_second": 2.932,
+    "train_steps_per_second": 0.183
+}

LLM-Detector-V5-11w/checkpoint-12000/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: ./Qwen-14B-Chat
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

LLM-Detector-V5-11w/checkpoint-12000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Qwen-14B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V5-11w/checkpoint-12000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4e56d160cf7490138ad2318e65a682c847563f5905bfc743a291b2b35caa7b
+size 26243102

LLM-Detector-V5-11w/checkpoint-12000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33c417ba7224c09cfc45a2f433ce271e77b9f3643be2b792ba5258b20cd9662
+size 52496442

LLM-Detector-V5-11w/checkpoint-12000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210d36a326ab9ae3f9794cdb713f70f85060cd21ff6d38241d3c5871436a7529
+size 14244

LLM-Detector-V5-11w/checkpoint-12000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67f15ee785078ff296bbc591ab3e9dfc50cf8cddc42a477dfe677cda389ba0dd
+size 1064

LLM-Detector-V5-11w/checkpoint-12000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

LLM-Detector-V5-11w/checkpoint-12000/tokenization_qwen.py

@@ -0,0 +1,276 @@
+# Copyright (c) Alibaba Cloud.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Tokenization classes for QWen."""
+
+import base64
+import logging
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.getLogger(__name__)
+
+
+VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+ENDOFTEXT = "<|endoftext|>"
+IMSTART = "<|im_start|>"
+IMEND = "<|im_end|>"
+# as the default behavior is changed to allow special tokens in
+# regular texts, the surface forms of special tokens need to be
+# as different as possible to minimize the impact
+EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
+# changed to use actual index to avoid misconfiguration with vocabulary expansion
+SPECIAL_START_ID = 151643
+SPECIAL_TOKENS = tuple(
+    enumerate(
+        (
+            (
+                ENDOFTEXT,
+                IMSTART,
+                IMEND,
+            )
+            + EXTRAS
+        ),
+        start=SPECIAL_START_ID,
+    )
+)
+SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)
+
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    with open(tiktoken_bpe_file, "rb") as f:
+        contents = f.read()
+    return {
+        base64.b64decode(token): int(rank)
+        for token, rank in (line.split() for line in contents.splitlines() if line)
+    }
+
+
+class QWenTokenizer(PreTrainedTokenizer):
+    """QWen tokenizer."""
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    def __init__(
+        self,
+        vocab_file,
+        errors="replace",
+        extra_vocab_file=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        # how to handle errors in decoding UTF-8 byte sequences
+        # use ignore if you are in streaming inference
+        self.errors = errors  
+
+        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
+        self.special_tokens = {
+            token: index
+            for index, token in SPECIAL_TOKENS
+        }
+
+        # try load extra vocab from file
+        if extra_vocab_file is not None:
+            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
+            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
+            for token, index in extra_mergeable_ranks.items():
+                if token in self.mergeable_ranks:
+                    logger.info(f"extra token {token} exists, skipping")
+                    continue
+                if index in used_ids:
+                    logger.info(f'the index {index} for extra token {token} exists, skipping')
+                    continue
+                self.mergeable_ranks[token] = index
+            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this
+
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        assert (
+            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
+        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
+
+        self.decoder = {
+            v: k for k, v in self.mergeable_ranks.items()
+        }  # type: dict[int, bytes|str]
+        self.decoder.update({v: k for k, v in self.special_tokens.items()})
+
+        self.tokenizer = enc  # type: tiktoken.Encoding
+
+        self.eod_id = self.tokenizer.eot_token
+        self.im_start_id = self.special_tokens[IMSTART]
+        self.im_end_id = self.special_tokens[IMEND]
+
+    def __getstate__(self):
+        # for pickle lovers
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        # tokenizer is not python native; don't pass it; rebuild it
+        self.__dict__.update(state)
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        self.tokenizer = enc
+
+    def __len__(self) -> int:
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.special_tokens:
+                return self.special_tokens[tokens]
+            else:
+                return self.mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.special_tokens:
+                ids.append(self.special_tokens[token])
+            else:
+                ids.append(self.mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS_SET:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "qwen.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        if token in self.mergeable_ranks:
+            return self.mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.eod_id]
+        return self.tokenizer.decode(token_ids, errors=errors or self.errors)

LLM-Detector-V5-11w/checkpoint-12000/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 8192,
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "QWenTokenizer"
+}

LLM-Detector-V5-11w/checkpoint-12000/trainer_state.json

@@ -0,0 +1,739 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6144764723689078,
+  "eval_steps": 500,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9997567688496474e-05,
+      "loss": 2.8699,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9990172715142793e-05,
+      "loss": 0.0389,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.997781629993153e-05,
+      "loss": 0.0301,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9960500896052476e-05,
+      "loss": 0.0244,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.993822994123172e-05,
+      "loss": 0.0151,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9911007857049264e-05,
+      "loss": 0.012,
+      "step": 600
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.987884004806111e-05,
+      "loss": 0.0268,
+      "step": 700
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.984173290072626e-05,
+      "loss": 0.0187,
+      "step": 800
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.979969378213884e-05,
+      "loss": 0.0166,
+      "step": 900
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.975273103856537e-05,
+      "loss": 0.022,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.970085399378785e-05,
+      "loss": 0.0194,
+      "step": 1100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.964407294725254e-05,
+      "loss": 0.0182,
+      "step": 1200
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.958239917202523e-05,
+      "loss": 0.0204,
+      "step": 1300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.9515844912553106e-05,
+      "loss": 0.013,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.944442338223378e-05,
+      "loss": 0.0107,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.9368148760792e-05,
+      "loss": 0.0156,
+      "step": 1600
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9287036191464414e-05,
+      "loss": 0.0141,
+      "step": 1700
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.9201101777993116e-05,
+      "loss": 0.0104,
+      "step": 1800
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.911036258142853e-05,
+      "loss": 0.0087,
+      "step": 1900
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.9014836616742065e-05,
+      "loss": 0.013,
+      "step": 2000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.891454284924965e-05,
+      "loss": 0.0194,
+      "step": 2100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.8809501190846284e-05,
+      "loss": 0.0131,
+      "step": 2200
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.8699732496052965e-05,
+      "loss": 0.0135,
+      "step": 2300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.858525855787619e-05,
+      "loss": 0.0106,
+      "step": 2400
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.846610210348137e-05,
+      "loss": 0.0089,
+      "step": 2500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.8342286789680605e-05,
+      "loss": 0.0086,
+      "step": 2600
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.8213837198235996e-05,
+      "loss": 0.0035,
+      "step": 2700
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.8080778830979276e-05,
+      "loss": 0.0121,
+      "step": 2800
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.794313810474878e-05,
+      "loss": 0.0146,
+      "step": 2900
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.780094234614479e-05,
+      "loss": 0.0047,
+      "step": 3000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.765421978610418e-05,
+      "loss": 0.0096,
+      "step": 3100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.750299955429562e-05,
+      "loss": 0.0116,
+      "step": 3200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.734731167333625e-05,
+      "loss": 0.0192,
+      "step": 3300
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.718718705283113e-05,
+      "loss": 0.0111,
+      "step": 3400
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.702265748323661e-05,
+      "loss": 0.0114,
+      "step": 3500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.685375562954876e-05,
+      "loss": 0.0113,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.668051502481818e-05,
+      "loss": 0.0097,
+      "step": 3700
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.650297006349257e-05,
+      "loss": 0.0094,
+      "step": 3800
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.63211559945881e-05,
+      "loss": 0.0059,
+      "step": 3900
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.613699021830524e-05,
+      "loss": 0.0195,
+      "step": 4000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.59467888395669e-05,
+      "loss": 0.0088,
+      "step": 4100
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.575242877508777e-05,
+      "loss": 0.0087,
+      "step": 4200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.5553948612282607e-05,
+      "loss": 0.0088,
+      "step": 4300
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.5351387756552846e-05,
+      "loss": 0.0122,
+      "step": 4400
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.51447864234632e-05,
+      "loss": 0.0081,
+      "step": 4500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.4934185630757484e-05,
+      "loss": 0.0079,
+      "step": 4600
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.4719627190215064e-05,
+      "loss": 0.011,
+      "step": 4700
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.450115369934976e-05,
+      "loss": 0.0146,
+      "step": 4800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.427880853295274e-05,
+      "loss": 0.0057,
+      "step": 4900
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.4052635834481025e-05,
+      "loss": 0.0051,
+      "step": 5000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.3822680507293455e-05,
+      "loss": 0.006,
+      "step": 5100
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.358898820573581e-05,
+      "loss": 0.0127,
+      "step": 5200
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.3351605326076724e-05,
+      "loss": 0.0062,
+      "step": 5300
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.3110578997296416e-05,
+      "loss": 0.0157,
+      "step": 5400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.286595707172986e-05,
+      "loss": 0.0111,
+      "step": 5500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.261778811556646e-05,
+      "loss": 0.0141,
+      "step": 5600
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.236612139920786e-05,
+      "loss": 0.0093,
+      "step": 5700
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.2111006887486035e-05,
+      "loss": 0.0091,
+      "step": 5800
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.185249522974346e-05,
+      "loss": 0.0043,
+      "step": 5900
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.159063774977748e-05,
+      "loss": 0.0072,
+      "step": 6000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.1325486435650625e-05,
+      "loss": 0.0063,
+      "step": 6100
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.105709392936914e-05,
+      "loss": 0.005,
+      "step": 6200
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.0785513516431705e-05,
+      "loss": 0.0167,
+      "step": 6300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.051079911525031e-05,
+      "loss": 0.0068,
+      "step": 6400
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.023300526644557e-05,
+      "loss": 0.0076,
+      "step": 6500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.9952187122018435e-05,
+      "loss": 0.0123,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.966840043440054e-05,
+      "loss": 0.0074,
+      "step": 6700
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.9381701545385384e-05,
+      "loss": 0.0045,
+      "step": 6800
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.9092147374942454e-05,
+      "loss": 0.0141,
+      "step": 6900
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.87997954099166e-05,
+      "loss": 0.0036,
+      "step": 7000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.8504703692614795e-05,
+      "loss": 0.0077,
+      "step": 7100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.820693080928271e-05,
+      "loss": 0.0063,
+      "step": 7200
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.790653587847325e-05,
+      "loss": 0.0078,
+      "step": 7300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.760357853930936e-05,
+      "loss": 0.004,
+      "step": 7400
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.72981189396436e-05,
+      "loss": 0.003,
+      "step": 7500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.699021772411661e-05,
+      "loss": 0.0064,
+      "step": 7600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.667993602211695e-05,
+      "loss": 0.0047,
+      "step": 7700
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.636733543564481e-05,
+      "loss": 0.0031,
+      "step": 7800
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.605247802708175e-05,
+      "loss": 0.0015,
+      "step": 7900
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.5735426306869135e-05,
+      "loss": 0.0103,
+      "step": 8000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.5416243221097553e-05,
+      "loss": 0.0062,
+      "step": 8100
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.509499213900977e-05,
+      "loss": 0.0046,
+      "step": 8200
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.477497910387336e-05,
+      "loss": 0.0082,
+      "step": 8300
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.44498028479363e-05,
+      "loss": 0.0065,
+      "step": 8400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.412275046861546e-05,
+      "loss": 0.0025,
+      "step": 8500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.379388689748946e-05,
+      "loss": 0.0047,
+      "step": 8600
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.346327742572318e-05,
+      "loss": 0.0028,
+      "step": 8700
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.3130987691105155e-05,
+      "loss": 0.0037,
+      "step": 8800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.279708366501608e-05,
+      "loss": 0.0067,
+      "step": 8900
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.246163163933119e-05,
+      "loss": 0.0045,
+      "step": 9000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.2124698213258904e-05,
+      "loss": 0.0038,
+      "step": 9100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.178635028011855e-05,
+      "loss": 0.0103,
+      "step": 9200
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.144665501405963e-05,
+      "loss": 0.0061,
+      "step": 9300
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.110567985672535e-05,
+      "loss": 0.0042,
+      "step": 9400
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.076349250386302e-05,
+      "loss": 0.0058,
+      "step": 9500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.0420160891884115e-05,
+      "loss": 0.0077,
+      "step": 9600
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.0075753184376354e-05,
+      "loss": 0.0036,
+      "step": 9700
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.9730337758570913e-05,
+      "loss": 0.007,
+      "step": 9800
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.938398319176699e-05,
+      "loss": 0.0073,
+      "step": 9900
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.903675824771684e-05,
+      "loss": 0.0053,
+      "step": 10000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.8688731862973677e-05,
+      "loss": 0.0074,
+      "step": 10100
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.833997313320535e-05,
+      "loss": 0.004,
+      "step": 10200
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.799055129947631e-05,
+      "loss": 0.003,
+      "step": 10300
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.7644038601038813e-05,
+      "loss": 0.0061,
+      "step": 10400
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.7293503693483008e-05,
+      "loss": 0.0044,
+      "step": 10500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6942513443527008e-05,
+      "loss": 0.0029,
+      "step": 10600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6591137535271742e-05,
+      "loss": 0.001,
+      "step": 10700
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.6239445729385104e-05,
+      "loss": 0.0047,
+      "step": 10800
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5887507849251914e-05,
+      "loss": 0.005,
+      "step": 10900
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5535393767111533e-05,
+      "loss": 0.0023,
+      "step": 11000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5183173390185736e-05,
+      "loss": 0.003,
+      "step": 11100
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.483091664679959e-05,
+      "loss": 0.0016,
+      "step": 11200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.44786934724982e-05,
+      "loss": 0.0027,
+      "step": 11300
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.4126573796162015e-05,
+      "loss": 0.003,
+      "step": 11400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.377462752612344e-05,
+      "loss": 0.002,
+      "step": 11500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.3422924536287548e-05,
+      "loss": 0.0026,
+      "step": 11600
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.307153465225958e-05,
+      "loss": 0.0037,
+      "step": 11700
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.272052763748209e-05,
+      "loss": 0.0063,
+      "step": 11800
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.2369973179384445e-05,
+      "loss": 0.0046,
+      "step": 11900
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.201994087554733e-05,
+      "loss": 0.0094,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 22296,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "total_flos": 1.9310189130989568e+18,
+  "trial_name": null,
+  "trial_params": null
+}

LLM-Detector-V5-11w/checkpoint-12000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a6604f99a4d8b8974d5d75cff26a2d414536f9959193cd5fdb32762398d2f1
+size 4600

LLM-Detector-V5-11w/checkpoint-15000/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: ./Qwen-14B-Chat
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

LLM-Detector-V5-11w/checkpoint-15000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Qwen-14B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V5-11w/checkpoint-15000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e3ade88c7690530234531f5ea3ba1dafb74162f68a6a4c2b8854bf7bb98313
+size 26243102

LLM-Detector-V5-11w/checkpoint-15000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261495d3911e1b36673858fccc3636350bf81734d6a63cbe6807d07565207f9b
+size 52496442

LLM-Detector-V5-11w/checkpoint-15000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092fd626805236851c2298469fb04906492bc35a31861f1e7955e1bef1d7670e
+size 14244

LLM-Detector-V5-11w/checkpoint-15000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea05cc55f2f45f53b449edaad91d7b12c981326c2d9b625bf8e619db7e03be2
+size 1064

LLM-Detector-V5-11w/checkpoint-15000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

LLM-Detector-V5-11w/checkpoint-15000/tokenization_qwen.py

@@ -0,0 +1,276 @@
+# Copyright (c) Alibaba Cloud.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Tokenization classes for QWen."""
+
+import base64
+import logging
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.getLogger(__name__)
+
+
+VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+ENDOFTEXT = "<|endoftext|>"
+IMSTART = "<|im_start|>"
+IMEND = "<|im_end|>"
+# as the default behavior is changed to allow special tokens in
+# regular texts, the surface forms of special tokens need to be
+# as different as possible to minimize the impact
+EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
+# changed to use actual index to avoid misconfiguration with vocabulary expansion
+SPECIAL_START_ID = 151643
+SPECIAL_TOKENS = tuple(
+    enumerate(
+        (
+            (
+                ENDOFTEXT,
+                IMSTART,
+                IMEND,
+            )
+            + EXTRAS
+        ),
+        start=SPECIAL_START_ID,
+    )
+)
+SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)
+
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    with open(tiktoken_bpe_file, "rb") as f:
+        contents = f.read()
+    return {
+        base64.b64decode(token): int(rank)
+        for token, rank in (line.split() for line in contents.splitlines() if line)
+    }
+
+
+class QWenTokenizer(PreTrainedTokenizer):
+    """QWen tokenizer."""
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    def __init__(
+        self,
+        vocab_file,
+        errors="replace",
+        extra_vocab_file=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        # how to handle errors in decoding UTF-8 byte sequences
+        # use ignore if you are in streaming inference
+        self.errors = errors  
+
+        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
+        self.special_tokens = {
+            token: index
+            for index, token in SPECIAL_TOKENS
+        }
+
+        # try load extra vocab from file
+        if extra_vocab_file is not None:
+            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
+            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
+            for token, index in extra_mergeable_ranks.items():
+                if token in self.mergeable_ranks:
+                    logger.info(f"extra token {token} exists, skipping")
+                    continue
+                if index in used_ids:
+                    logger.info(f'the index {index} for extra token {token} exists, skipping')
+                    continue
+                self.mergeable_ranks[token] = index
+            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this
+
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        assert (
+            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
+        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
+
+        self.decoder = {
+            v: k for k, v in self.mergeable_ranks.items()
+        }  # type: dict[int, bytes|str]
+        self.decoder.update({v: k for k, v in self.special_tokens.items()})
+
+        self.tokenizer = enc  # type: tiktoken.Encoding
+
+        self.eod_id = self.tokenizer.eot_token
+        self.im_start_id = self.special_tokens[IMSTART]
+        self.im_end_id = self.special_tokens[IMEND]
+
+    def __getstate__(self):
+        # for pickle lovers
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        # tokenizer is not python native; don't pass it; rebuild it
+        self.__dict__.update(state)
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        self.tokenizer = enc
+
+    def __len__(self) -> int:
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.special_tokens:
+                return self.special_tokens[tokens]
+            else:
+                return self.mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.special_tokens:
+                ids.append(self.special_tokens[token])
+            else:
+                ids.append(self.mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS_SET:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "qwen.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        if token in self.mergeable_ranks:
+            return self.mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.eod_id]
+        return self.tokenizer.decode(token_ids, errors=errors or self.errors)

LLM-Detector-V5-11w/checkpoint-15000/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 8192,
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "QWenTokenizer"
+}

LLM-Detector-V5-11w/checkpoint-15000/trainer_state.json

@@ -0,0 +1,919 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.018095590461135,
+  "eval_steps": 500,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9997567688496474e-05,
+      "loss": 2.8699,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9990172715142793e-05,
+      "loss": 0.0389,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.997781629993153e-05,
+      "loss": 0.0301,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9960500896052476e-05,
+      "loss": 0.0244,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.993822994123172e-05,
+      "loss": 0.0151,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9911007857049264e-05,
+      "loss": 0.012,
+      "step": 600
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.987884004806111e-05,
+      "loss": 0.0268,
+      "step": 700
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.984173290072626e-05,
+      "loss": 0.0187,
+      "step": 800
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.979969378213884e-05,
+      "loss": 0.0166,
+      "step": 900
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.975273103856537e-05,
+      "loss": 0.022,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.970085399378785e-05,
+      "loss": 0.0194,
+      "step": 1100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.964407294725254e-05,
+      "loss": 0.0182,
+      "step": 1200
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.958239917202523e-05,
+      "loss": 0.0204,
+      "step": 1300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.9515844912553106e-05,
+      "loss": 0.013,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.944442338223378e-05,
+      "loss": 0.0107,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.9368148760792e-05,
+      "loss": 0.0156,
+      "step": 1600
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9287036191464414e-05,
+      "loss": 0.0141,
+      "step": 1700
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.9201101777993116e-05,
+      "loss": 0.0104,
+      "step": 1800
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.911036258142853e-05,
+      "loss": 0.0087,
+      "step": 1900
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.9014836616742065e-05,
+      "loss": 0.013,
+      "step": 2000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.891454284924965e-05,
+      "loss": 0.0194,
+      "step": 2100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.8809501190846284e-05,
+      "loss": 0.0131,
+      "step": 2200
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.8699732496052965e-05,
+      "loss": 0.0135,
+      "step": 2300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.858525855787619e-05,
+      "loss": 0.0106,
+      "step": 2400
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.846610210348137e-05,
+      "loss": 0.0089,
+      "step": 2500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.8342286789680605e-05,
+      "loss": 0.0086,
+      "step": 2600
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.8213837198235996e-05,
+      "loss": 0.0035,
+      "step": 2700
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.8080778830979276e-05,
+      "loss": 0.0121,
+      "step": 2800
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.794313810474878e-05,
+      "loss": 0.0146,
+      "step": 2900
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.780094234614479e-05,
+      "loss": 0.0047,
+      "step": 3000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.765421978610418e-05,
+      "loss": 0.0096,
+      "step": 3100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.750299955429562e-05,
+      "loss": 0.0116,
+      "step": 3200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.734731167333625e-05,
+      "loss": 0.0192,
+      "step": 3300
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.718718705283113e-05,
+      "loss": 0.0111,
+      "step": 3400
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.702265748323661e-05,
+      "loss": 0.0114,
+      "step": 3500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.685375562954876e-05,
+      "loss": 0.0113,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.668051502481818e-05,
+      "loss": 0.0097,
+      "step": 3700
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.650297006349257e-05,
+      "loss": 0.0094,
+      "step": 3800
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.63211559945881e-05,
+      "loss": 0.0059,
+      "step": 3900
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.613699021830524e-05,
+      "loss": 0.0195,
+      "step": 4000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.59467888395669e-05,
+      "loss": 0.0088,
+      "step": 4100
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.575242877508777e-05,
+      "loss": 0.0087,
+      "step": 4200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.5553948612282607e-05,
+      "loss": 0.0088,
+      "step": 4300
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.5351387756552846e-05,
+      "loss": 0.0122,
+      "step": 4400
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.51447864234632e-05,
+      "loss": 0.0081,
+      "step": 4500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.4934185630757484e-05,
+      "loss": 0.0079,
+      "step": 4600
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.4719627190215064e-05,
+      "loss": 0.011,
+      "step": 4700
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.450115369934976e-05,
+      "loss": 0.0146,
+      "step": 4800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.427880853295274e-05,
+      "loss": 0.0057,
+      "step": 4900
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.4052635834481025e-05,
+      "loss": 0.0051,
+      "step": 5000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.3822680507293455e-05,
+      "loss": 0.006,
+      "step": 5100
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.358898820573581e-05,
+      "loss": 0.0127,
+      "step": 5200
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.3351605326076724e-05,
+      "loss": 0.0062,
+      "step": 5300
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.3110578997296416e-05,
+      "loss": 0.0157,
+      "step": 5400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.286595707172986e-05,
+      "loss": 0.0111,
+      "step": 5500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.261778811556646e-05,
+      "loss": 0.0141,
+      "step": 5600
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.236612139920786e-05,
+      "loss": 0.0093,
+      "step": 5700
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.2111006887486035e-05,
+      "loss": 0.0091,
+      "step": 5800
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.185249522974346e-05,
+      "loss": 0.0043,
+      "step": 5900
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.159063774977748e-05,
+      "loss": 0.0072,
+      "step": 6000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.1325486435650625e-05,
+      "loss": 0.0063,
+      "step": 6100
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.105709392936914e-05,
+      "loss": 0.005,
+      "step": 6200
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.0785513516431705e-05,
+      "loss": 0.0167,
+      "step": 6300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.051079911525031e-05,
+      "loss": 0.0068,
+      "step": 6400
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.023300526644557e-05,
+      "loss": 0.0076,
+      "step": 6500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.9952187122018435e-05,
+      "loss": 0.0123,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.966840043440054e-05,
+      "loss": 0.0074,
+      "step": 6700
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.9381701545385384e-05,
+      "loss": 0.0045,
+      "step": 6800
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.9092147374942454e-05,
+      "loss": 0.0141,
+      "step": 6900
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.87997954099166e-05,
+      "loss": 0.0036,
+      "step": 7000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.8504703692614795e-05,
+      "loss": 0.0077,
+      "step": 7100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.820693080928271e-05,
+      "loss": 0.0063,
+      "step": 7200
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.790653587847325e-05,
+      "loss": 0.0078,
+      "step": 7300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.760357853930936e-05,
+      "loss": 0.004,
+      "step": 7400
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.72981189396436e-05,
+      "loss": 0.003,
+      "step": 7500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.699021772411661e-05,
+      "loss": 0.0064,
+      "step": 7600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.667993602211695e-05,
+      "loss": 0.0047,
+      "step": 7700
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.636733543564481e-05,
+      "loss": 0.0031,
+      "step": 7800
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.605247802708175e-05,
+      "loss": 0.0015,
+      "step": 7900
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.5735426306869135e-05,
+      "loss": 0.0103,
+      "step": 8000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.5416243221097553e-05,
+      "loss": 0.0062,
+      "step": 8100
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.509499213900977e-05,
+      "loss": 0.0046,
+      "step": 8200
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.477497910387336e-05,
+      "loss": 0.0082,
+      "step": 8300
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.44498028479363e-05,
+      "loss": 0.0065,
+      "step": 8400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.412275046861546e-05,
+      "loss": 0.0025,
+      "step": 8500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.379388689748946e-05,
+      "loss": 0.0047,
+      "step": 8600
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.346327742572318e-05,
+      "loss": 0.0028,
+      "step": 8700
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.3130987691105155e-05,
+      "loss": 0.0037,
+      "step": 8800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.279708366501608e-05,
+      "loss": 0.0067,
+      "step": 8900
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.246163163933119e-05,
+      "loss": 0.0045,
+      "step": 9000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.2124698213258904e-05,
+      "loss": 0.0038,
+      "step": 9100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.178635028011855e-05,
+      "loss": 0.0103,
+      "step": 9200
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.144665501405963e-05,
+      "loss": 0.0061,
+      "step": 9300
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.110567985672535e-05,
+      "loss": 0.0042,
+      "step": 9400
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.076349250386302e-05,
+      "loss": 0.0058,
+      "step": 9500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.0420160891884115e-05,
+      "loss": 0.0077,
+      "step": 9600
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.0075753184376354e-05,
+      "loss": 0.0036,
+      "step": 9700
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.9730337758570913e-05,
+      "loss": 0.007,
+      "step": 9800
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.938398319176699e-05,
+      "loss": 0.0073,
+      "step": 9900
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.903675824771684e-05,
+      "loss": 0.0053,
+      "step": 10000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.8688731862973677e-05,
+      "loss": 0.0074,
+      "step": 10100
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.833997313320535e-05,
+      "loss": 0.004,
+      "step": 10200
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.799055129947631e-05,
+      "loss": 0.003,
+      "step": 10300
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.7644038601038813e-05,
+      "loss": 0.0061,
+      "step": 10400
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.7293503693483008e-05,
+      "loss": 0.0044,
+      "step": 10500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6942513443527008e-05,
+      "loss": 0.0029,
+      "step": 10600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6591137535271742e-05,
+      "loss": 0.001,
+      "step": 10700
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.6239445729385104e-05,
+      "loss": 0.0047,
+      "step": 10800
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5887507849251914e-05,
+      "loss": 0.005,
+      "step": 10900
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5535393767111533e-05,
+      "loss": 0.0023,
+      "step": 11000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5183173390185736e-05,
+      "loss": 0.003,
+      "step": 11100
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.483091664679959e-05,
+      "loss": 0.0016,
+      "step": 11200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.44786934724982e-05,
+      "loss": 0.0027,
+      "step": 11300
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.4126573796162015e-05,
+      "loss": 0.003,
+      "step": 11400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.377462752612344e-05,
+      "loss": 0.002,
+      "step": 11500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.3422924536287548e-05,
+      "loss": 0.0026,
+      "step": 11600
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.307153465225958e-05,
+      "loss": 0.0037,
+      "step": 11700
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.272052763748209e-05,
+      "loss": 0.0063,
+      "step": 11800
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.2369973179384445e-05,
+      "loss": 0.0046,
+      "step": 11900
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.201994087554733e-05,
+      "loss": 0.0094,
+      "step": 12000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.167050021988514e-05,
+      "loss": 0.0043,
+      "step": 12100
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.1321720588848995e-05,
+      "loss": 0.0024,
+      "step": 12200
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.097367122765301e-05,
+      "loss": 0.0029,
+      "step": 12300
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.0626421236526656e-05,
+      "loss": 0.0036,
+      "step": 12400
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.0280039556995902e-05,
+      "loss": 0.0045,
+      "step": 12500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.9934594958195834e-05,
+      "loss": 0.002,
+      "step": 12600
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.9590156023217553e-05,
+      "loss": 0.0039,
+      "step": 12700
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.9246791135491982e-05,
+      "loss": 0.0038,
+      "step": 12800
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.8904568465213288e-05,
+      "loss": 0.0015,
+      "step": 12900
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.8563555955804683e-05,
+      "loss": 0.0034,
+      "step": 13000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8227212109768717e-05,
+      "loss": 0.0047,
+      "step": 13100
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.7888808991743948e-05,
+      "loss": 0.002,
+      "step": 13200
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.7551817699124613e-05,
+      "loss": 0.0036,
+      "step": 13300
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.721630513671862e-05,
+      "loss": 0.0055,
+      "step": 13400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.6882337915753093e-05,
+      "loss": 0.0054,
+      "step": 13500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.65499823406497e-05,
+      "loss": 0.0024,
+      "step": 13600
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.621930439586083e-05,
+      "loss": 0.0057,
+      "step": 13700
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.5890369732769356e-05,
+      "loss": 0.0055,
+      "step": 13800
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.5563243656654454e-05,
+      "loss": 0.0025,
+      "step": 13900
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.5237991113726185e-05,
+      "loss": 0.0024,
+      "step": 14000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.4914676678231354e-05,
+      "loss": 0.0037,
+      "step": 14100
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.4593364539633242e-05,
+      "loss": 0.0056,
+      "step": 14200
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.4274118489867638e-05,
+      "loss": 0.0017,
+      "step": 14300
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.3957001910677942e-05,
+      "loss": 0.0061,
+      "step": 14400
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.3642077761031574e-05,
+      "loss": 0.0011,
+      "step": 14500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.3329408564620358e-05,
+      "loss": 0.0063,
+      "step": 14600
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.3019056397447415e-05,
+      "loss": 0.0005,
+      "step": 14700
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2711082875502745e-05,
+      "loss": 0.0065,
+      "step": 14800
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2405549142530348e-05,
+      "loss": 0.0019,
+      "step": 14900
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.2102515857888976e-05,
+      "loss": 0.0007,
+      "step": 15000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 22296,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "total_flos": 2.415914809978061e+18,
+  "trial_name": null,
+  "trial_params": null
+}

LLM-Detector-V5-11w/checkpoint-15000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a6604f99a4d8b8974d5d75cff26a2d414536f9959193cd5fdb32762398d2f1
+size 4600

LLM-Detector-V5-11w/checkpoint-18000/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: ./Qwen-14B-Chat
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

LLM-Detector-V5-11w/checkpoint-18000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Qwen-14B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V5-11w/checkpoint-18000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b84f040810abec4b1d058fa65d87d3914a6644ff60a8b71cd9cb57516ac29e4
+size 26243102

LLM-Detector-V5-11w/checkpoint-18000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:599ef45aa70ef147baf3eed450e8ea1c1b79d43b09246edbf2d46c8dddf631a6
+size 52496442

LLM-Detector-V5-11w/checkpoint-18000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffef474a61b5d594d02a14df6e47f6516d65561a1e6dc4f046d212671d47185
+size 14244

LLM-Detector-V5-11w/checkpoint-18000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ceeb9aa46e20b83a8a047535f01f9c43262f16f9d910408401c88cb64c2085
+size 1064

LLM-Detector-V5-11w/checkpoint-18000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

LLM-Detector-V5-11w/checkpoint-18000/tokenization_qwen.py

@@ -0,0 +1,276 @@
+# Copyright (c) Alibaba Cloud.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Tokenization classes for QWen."""
+
+import base64
+import logging
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.getLogger(__name__)
+
+
+VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+ENDOFTEXT = "<|endoftext|>"
+IMSTART = "<|im_start|>"
+IMEND = "<|im_end|>"
+# as the default behavior is changed to allow special tokens in
+# regular texts, the surface forms of special tokens need to be
+# as different as possible to minimize the impact
+EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
+# changed to use actual index to avoid misconfiguration with vocabulary expansion
+SPECIAL_START_ID = 151643
+SPECIAL_TOKENS = tuple(
+    enumerate(
+        (
+            (
+                ENDOFTEXT,
+                IMSTART,
+                IMEND,
+            )
+            + EXTRAS
+        ),
+        start=SPECIAL_START_ID,
+    )
+)
+SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)
+
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    with open(tiktoken_bpe_file, "rb") as f:
+        contents = f.read()
+    return {
+        base64.b64decode(token): int(rank)
+        for token, rank in (line.split() for line in contents.splitlines() if line)
+    }
+
+
+class QWenTokenizer(PreTrainedTokenizer):
+    """QWen tokenizer."""
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    def __init__(
+        self,
+        vocab_file,
+        errors="replace",
+        extra_vocab_file=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        # how to handle errors in decoding UTF-8 byte sequences
+        # use ignore if you are in streaming inference
+        self.errors = errors  
+
+        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
+        self.special_tokens = {
+            token: index
+            for index, token in SPECIAL_TOKENS
+        }
+
+        # try load extra vocab from file
+        if extra_vocab_file is not None:
+            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
+            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
+            for token, index in extra_mergeable_ranks.items():
+                if token in self.mergeable_ranks:
+                    logger.info(f"extra token {token} exists, skipping")
+                    continue
+                if index in used_ids:
+                    logger.info(f'the index {index} for extra token {token} exists, skipping')
+                    continue
+                self.mergeable_ranks[token] = index
+            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this
+
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        assert (
+            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
+        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
+
+        self.decoder = {
+            v: k for k, v in self.mergeable_ranks.items()
+        }  # type: dict[int, bytes|str]
+        self.decoder.update({v: k for k, v in self.special_tokens.items()})
+
+        self.tokenizer = enc  # type: tiktoken.Encoding
+
+        self.eod_id = self.tokenizer.eot_token
+        self.im_start_id = self.special_tokens[IMSTART]
+        self.im_end_id = self.special_tokens[IMEND]
+
+    def __getstate__(self):
+        # for pickle lovers
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        # tokenizer is not python native; don't pass it; rebuild it
+        self.__dict__.update(state)
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        self.tokenizer = enc
+
+    def __len__(self) -> int:
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.special_tokens:
+                return self.special_tokens[tokens]
+            else:
+                return self.mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.special_tokens:
+                ids.append(self.special_tokens[token])
+            else:
+                ids.append(self.mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS_SET:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "qwen.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        if token in self.mergeable_ranks:
+            return self.mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.eod_id]
+        return self.tokenizer.decode(token_ids, errors=errors or self.errors)

LLM-Detector-V5-11w/checkpoint-18000/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 8192,
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "QWenTokenizer"
+}

LLM-Detector-V5-11w/checkpoint-18000/trainer_state.json

@@ -0,0 +1,1099 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.421714708553362,
+  "eval_steps": 500,
+  "global_step": 18000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9997567688496474e-05,
+      "loss": 2.8699,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9990172715142793e-05,
+      "loss": 0.0389,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.997781629993153e-05,
+      "loss": 0.0301,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9960500896052476e-05,
+      "loss": 0.0244,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.993822994123172e-05,
+      "loss": 0.0151,
+      "step": 500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.9911007857049264e-05,
+      "loss": 0.012,
+      "step": 600
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.987884004806111e-05,
+      "loss": 0.0268,
+      "step": 700
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.984173290072626e-05,
+      "loss": 0.0187,
+      "step": 800
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.979969378213884e-05,
+      "loss": 0.0166,
+      "step": 900
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.975273103856537e-05,
+      "loss": 0.022,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.970085399378785e-05,
+      "loss": 0.0194,
+      "step": 1100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.964407294725254e-05,
+      "loss": 0.0182,
+      "step": 1200
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.958239917202523e-05,
+      "loss": 0.0204,
+      "step": 1300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.9515844912553106e-05,
+      "loss": 0.013,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.944442338223378e-05,
+      "loss": 0.0107,
+      "step": 1500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.9368148760792e-05,
+      "loss": 0.0156,
+      "step": 1600
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.9287036191464414e-05,
+      "loss": 0.0141,
+      "step": 1700
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.9201101777993116e-05,
+      "loss": 0.0104,
+      "step": 1800
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.911036258142853e-05,
+      "loss": 0.0087,
+      "step": 1900
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.9014836616742065e-05,
+      "loss": 0.013,
+      "step": 2000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.891454284924965e-05,
+      "loss": 0.0194,
+      "step": 2100
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.8809501190846284e-05,
+      "loss": 0.0131,
+      "step": 2200
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.8699732496052965e-05,
+      "loss": 0.0135,
+      "step": 2300
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.858525855787619e-05,
+      "loss": 0.0106,
+      "step": 2400
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.846610210348137e-05,
+      "loss": 0.0089,
+      "step": 2500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.8342286789680605e-05,
+      "loss": 0.0086,
+      "step": 2600
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.8213837198235996e-05,
+      "loss": 0.0035,
+      "step": 2700
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.8080778830979276e-05,
+      "loss": 0.0121,
+      "step": 2800
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.794313810474878e-05,
+      "loss": 0.0146,
+      "step": 2900
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.780094234614479e-05,
+      "loss": 0.0047,
+      "step": 3000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.765421978610418e-05,
+      "loss": 0.0096,
+      "step": 3100
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.750299955429562e-05,
+      "loss": 0.0116,
+      "step": 3200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.734731167333625e-05,
+      "loss": 0.0192,
+      "step": 3300
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.718718705283113e-05,
+      "loss": 0.0111,
+      "step": 3400
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.702265748323661e-05,
+      "loss": 0.0114,
+      "step": 3500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.685375562954876e-05,
+      "loss": 0.0113,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.668051502481818e-05,
+      "loss": 0.0097,
+      "step": 3700
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.650297006349257e-05,
+      "loss": 0.0094,
+      "step": 3800
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.63211559945881e-05,
+      "loss": 0.0059,
+      "step": 3900
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.613699021830524e-05,
+      "loss": 0.0195,
+      "step": 4000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.59467888395669e-05,
+      "loss": 0.0088,
+      "step": 4100
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.575242877508777e-05,
+      "loss": 0.0087,
+      "step": 4200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.5553948612282607e-05,
+      "loss": 0.0088,
+      "step": 4300
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.5351387756552846e-05,
+      "loss": 0.0122,
+      "step": 4400
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.51447864234632e-05,
+      "loss": 0.0081,
+      "step": 4500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.4934185630757484e-05,
+      "loss": 0.0079,
+      "step": 4600
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.4719627190215064e-05,
+      "loss": 0.011,
+      "step": 4700
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.450115369934976e-05,
+      "loss": 0.0146,
+      "step": 4800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.427880853295274e-05,
+      "loss": 0.0057,
+      "step": 4900
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.4052635834481025e-05,
+      "loss": 0.0051,
+      "step": 5000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.3822680507293455e-05,
+      "loss": 0.006,
+      "step": 5100
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.358898820573581e-05,
+      "loss": 0.0127,
+      "step": 5200
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.3351605326076724e-05,
+      "loss": 0.0062,
+      "step": 5300
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.3110578997296416e-05,
+      "loss": 0.0157,
+      "step": 5400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.286595707172986e-05,
+      "loss": 0.0111,
+      "step": 5500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.261778811556646e-05,
+      "loss": 0.0141,
+      "step": 5600
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 4.236612139920786e-05,
+      "loss": 0.0093,
+      "step": 5700
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.2111006887486035e-05,
+      "loss": 0.0091,
+      "step": 5800
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.185249522974346e-05,
+      "loss": 0.0043,
+      "step": 5900
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.159063774977748e-05,
+      "loss": 0.0072,
+      "step": 6000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 4.1325486435650625e-05,
+      "loss": 0.0063,
+      "step": 6100
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 4.105709392936914e-05,
+      "loss": 0.005,
+      "step": 6200
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.0785513516431705e-05,
+      "loss": 0.0167,
+      "step": 6300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.051079911525031e-05,
+      "loss": 0.0068,
+      "step": 6400
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.023300526644557e-05,
+      "loss": 0.0076,
+      "step": 6500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.9952187122018435e-05,
+      "loss": 0.0123,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.966840043440054e-05,
+      "loss": 0.0074,
+      "step": 6700
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.9381701545385384e-05,
+      "loss": 0.0045,
+      "step": 6800
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.9092147374942454e-05,
+      "loss": 0.0141,
+      "step": 6900
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.87997954099166e-05,
+      "loss": 0.0036,
+      "step": 7000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3.8504703692614795e-05,
+      "loss": 0.0077,
+      "step": 7100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.820693080928271e-05,
+      "loss": 0.0063,
+      "step": 7200
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.790653587847325e-05,
+      "loss": 0.0078,
+      "step": 7300
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.760357853930936e-05,
+      "loss": 0.004,
+      "step": 7400
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.72981189396436e-05,
+      "loss": 0.003,
+      "step": 7500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.699021772411661e-05,
+      "loss": 0.0064,
+      "step": 7600
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.667993602211695e-05,
+      "loss": 0.0047,
+      "step": 7700
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.636733543564481e-05,
+      "loss": 0.0031,
+      "step": 7800
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.605247802708175e-05,
+      "loss": 0.0015,
+      "step": 7900
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.5735426306869135e-05,
+      "loss": 0.0103,
+      "step": 8000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.5416243221097553e-05,
+      "loss": 0.0062,
+      "step": 8100
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.509499213900977e-05,
+      "loss": 0.0046,
+      "step": 8200
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.477497910387336e-05,
+      "loss": 0.0082,
+      "step": 8300
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.44498028479363e-05,
+      "loss": 0.0065,
+      "step": 8400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.412275046861546e-05,
+      "loss": 0.0025,
+      "step": 8500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.379388689748946e-05,
+      "loss": 0.0047,
+      "step": 8600
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.346327742572318e-05,
+      "loss": 0.0028,
+      "step": 8700
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.3130987691105155e-05,
+      "loss": 0.0037,
+      "step": 8800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.279708366501608e-05,
+      "loss": 0.0067,
+      "step": 8900
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.246163163933119e-05,
+      "loss": 0.0045,
+      "step": 9000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 3.2124698213258904e-05,
+      "loss": 0.0038,
+      "step": 9100
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.178635028011855e-05,
+      "loss": 0.0103,
+      "step": 9200
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.144665501405963e-05,
+      "loss": 0.0061,
+      "step": 9300
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.110567985672535e-05,
+      "loss": 0.0042,
+      "step": 9400
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 3.076349250386302e-05,
+      "loss": 0.0058,
+      "step": 9500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.0420160891884115e-05,
+      "loss": 0.0077,
+      "step": 9600
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.0075753184376354e-05,
+      "loss": 0.0036,
+      "step": 9700
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.9730337758570913e-05,
+      "loss": 0.007,
+      "step": 9800
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.938398319176699e-05,
+      "loss": 0.0073,
+      "step": 9900
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.903675824771684e-05,
+      "loss": 0.0053,
+      "step": 10000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.8688731862973677e-05,
+      "loss": 0.0074,
+      "step": 10100
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.833997313320535e-05,
+      "loss": 0.004,
+      "step": 10200
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.799055129947631e-05,
+      "loss": 0.003,
+      "step": 10300
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.7644038601038813e-05,
+      "loss": 0.0061,
+      "step": 10400
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.7293503693483008e-05,
+      "loss": 0.0044,
+      "step": 10500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6942513443527008e-05,
+      "loss": 0.0029,
+      "step": 10600
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2.6591137535271742e-05,
+      "loss": 0.001,
+      "step": 10700
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.6239445729385104e-05,
+      "loss": 0.0047,
+      "step": 10800
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 2.5887507849251914e-05,
+      "loss": 0.005,
+      "step": 10900
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 2.5535393767111533e-05,
+      "loss": 0.0023,
+      "step": 11000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5183173390185736e-05,
+      "loss": 0.003,
+      "step": 11100
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.483091664679959e-05,
+      "loss": 0.0016,
+      "step": 11200
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.44786934724982e-05,
+      "loss": 0.0027,
+      "step": 11300
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.4126573796162015e-05,
+      "loss": 0.003,
+      "step": 11400
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.377462752612344e-05,
+      "loss": 0.002,
+      "step": 11500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.3422924536287548e-05,
+      "loss": 0.0026,
+      "step": 11600
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 2.307153465225958e-05,
+      "loss": 0.0037,
+      "step": 11700
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.272052763748209e-05,
+      "loss": 0.0063,
+      "step": 11800
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.2369973179384445e-05,
+      "loss": 0.0046,
+      "step": 11900
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.201994087554733e-05,
+      "loss": 0.0094,
+      "step": 12000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.167050021988514e-05,
+      "loss": 0.0043,
+      "step": 12100
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.1321720588848995e-05,
+      "loss": 0.0024,
+      "step": 12200
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.097367122765301e-05,
+      "loss": 0.0029,
+      "step": 12300
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.0626421236526656e-05,
+      "loss": 0.0036,
+      "step": 12400
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.0280039556995902e-05,
+      "loss": 0.0045,
+      "step": 12500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.9934594958195834e-05,
+      "loss": 0.002,
+      "step": 12600
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.9590156023217553e-05,
+      "loss": 0.0039,
+      "step": 12700
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.9246791135491982e-05,
+      "loss": 0.0038,
+      "step": 12800
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.8904568465213288e-05,
+      "loss": 0.0015,
+      "step": 12900
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.8563555955804683e-05,
+      "loss": 0.0034,
+      "step": 13000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.8227212109768717e-05,
+      "loss": 0.0047,
+      "step": 13100
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.7888808991743948e-05,
+      "loss": 0.002,
+      "step": 13200
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.7551817699124613e-05,
+      "loss": 0.0036,
+      "step": 13300
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.721630513671862e-05,
+      "loss": 0.0055,
+      "step": 13400
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.6882337915753093e-05,
+      "loss": 0.0054,
+      "step": 13500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.65499823406497e-05,
+      "loss": 0.0024,
+      "step": 13600
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.621930439586083e-05,
+      "loss": 0.0057,
+      "step": 13700
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.5890369732769356e-05,
+      "loss": 0.0055,
+      "step": 13800
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.5563243656654454e-05,
+      "loss": 0.0025,
+      "step": 13900
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.5237991113726185e-05,
+      "loss": 0.0024,
+      "step": 14000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.4914676678231354e-05,
+      "loss": 0.0037,
+      "step": 14100
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.4593364539633242e-05,
+      "loss": 0.0056,
+      "step": 14200
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.4274118489867638e-05,
+      "loss": 0.0017,
+      "step": 14300
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.3957001910677942e-05,
+      "loss": 0.0061,
+      "step": 14400
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.3642077761031574e-05,
+      "loss": 0.0011,
+      "step": 14500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.3329408564620358e-05,
+      "loss": 0.0063,
+      "step": 14600
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.3019056397447415e-05,
+      "loss": 0.0005,
+      "step": 14700
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2711082875502745e-05,
+      "loss": 0.0065,
+      "step": 14800
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.2405549142530348e-05,
+      "loss": 0.0019,
+      "step": 14900
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.2102515857888976e-05,
+      "loss": 0.0007,
+      "step": 15000
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.1802043184509044e-05,
+      "loss": 0.0008,
+      "step": 15100
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.1504190776948205e-05,
+      "loss": 0.0018,
+      "step": 15200
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.1209017769547758e-05,
+      "loss": 0.0002,
+      "step": 15300
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 1.0916582764692346e-05,
+      "loss": 0.0009,
+      "step": 15400
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.062694382117534e-05,
+      "loss": 0.0003,
+      "step": 15500
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.0340158442672049e-05,
+      "loss": 0.0018,
+      "step": 15600
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.0056283566323224e-05,
+      "loss": 0.0053,
+      "step": 15700
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.77537555143098e-06,
+      "loss": 0.0005,
+      "step": 15800
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.497490168269444e-06,
+      "loss": 0.0009,
+      "step": 15900
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.222682587012408e-06,
+      "loss": 0.0018,
+      "step": 16000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 8.951007366780059e-06,
+      "loss": 0.0003,
+      "step": 16100
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 8.682518444807017e-06,
+      "loss": 0.0003,
+      "step": 16200
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 8.417269125733923e-06,
+      "loss": 0.0023,
+      "step": 16300
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 8.155312071024505e-06,
+      "loss": 0.0008,
+      "step": 16400
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 7.896699288510437e-06,
+      "loss": 0.0002,
+      "step": 16500
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 7.64148212206594e-06,
+      "loss": 0.0009,
+      "step": 16600
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 7.389711241414119e-06,
+      "loss": 0.0003,
+      "step": 16700
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 7.141436632067294e-06,
+      "loss": 0.0001,
+      "step": 16800
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 6.896707585403029e-06,
+      "loss": 0.0006,
+      "step": 16900
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 6.655572688878073e-06,
+      "loss": 0.0009,
+      "step": 17000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 6.4180798163820085e-06,
+      "loss": 0.0002,
+      "step": 17100
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 6.184276118732538e-06,
+      "loss": 0.0009,
+      "step": 17200
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 5.954208014314419e-06,
+      "loss": 0.0018,
+      "step": 17300
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 5.727921179863712e-06,
+      "loss": 0.0014,
+      "step": 17400
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 5.505460541399343e-06,
+      "loss": 0.0006,
+      "step": 17500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 5.286870265303676e-06,
+      "loss": 0.0,
+      "step": 17600
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 5.074321001003329e-06,
+      "loss": 0.0004,
+      "step": 17700
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 4.863561094340846e-06,
+      "loss": 0.0005,
+      "step": 17800
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 4.656798990014011e-06,
+      "loss": 0.0026,
+      "step": 17900
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 4.454075737685456e-06,
+      "loss": 0.0002,
+      "step": 18000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 22296,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "total_flos": 2.899990453107917e+18,
+  "trial_name": null,
+  "trial_params": null
+}

LLM-Detector-V5-11w/checkpoint-18000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a6604f99a4d8b8974d5d75cff26a2d414536f9959193cd5fdb32762398d2f1
+size 4600

LLM-Detector-V5-11w/checkpoint-21000/README.md

@@ -0,0 +1,219 @@
+---
+library_name: peft
+base_model: ./Qwen-14B-Chat
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Data Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: QuantizationMethod.BITS_AND_BYTES
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: float16
+
+### Framework versions
+
+
+- PEFT 0.6.2

LLM-Detector-V5-11w/checkpoint-21000/adapter_config.json

@@ -0,0 +1,22 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./Qwen-14B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

LLM-Detector-V5-11w/checkpoint-21000/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9676e557f268125346b3cafb8bc11f0b945e39e8f5840ece332ce5ffbdaf7db5
+size 26243102

LLM-Detector-V5-11w/checkpoint-21000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d139866f1a7697e27b3d0a75fec4ce13c19f7f91e0d9c12607c2c42fe9287d
+size 52496442

LLM-Detector-V5-11w/checkpoint-21000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69dd10e027369fa679f0710061cf9a69c9ad685e2576c58aa25eeecc76db570
+size 14244

LLM-Detector-V5-11w/checkpoint-21000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fa4b00b1cba54897c2cbf8301611ceaa02033f2121ce9abb7ed43742023e50
+size 1064

LLM-Detector-V5-11w/checkpoint-21000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "additional_special_tokens": [
+    "<|im_end|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

LLM-Detector-V5-11w/checkpoint-21000/tokenization_qwen.py

@@ -0,0 +1,276 @@
+# Copyright (c) Alibaba Cloud.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Tokenization classes for QWen."""
+
+import base64
+import logging
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.getLogger(__name__)
+
+
+VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+ENDOFTEXT = "<|endoftext|>"
+IMSTART = "<|im_start|>"
+IMEND = "<|im_end|>"
+# as the default behavior is changed to allow special tokens in
+# regular texts, the surface forms of special tokens need to be
+# as different as possible to minimize the impact
+EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
+# changed to use actual index to avoid misconfiguration with vocabulary expansion
+SPECIAL_START_ID = 151643
+SPECIAL_TOKENS = tuple(
+    enumerate(
+        (
+            (
+                ENDOFTEXT,
+                IMSTART,
+                IMEND,
+            )
+            + EXTRAS
+        ),
+        start=SPECIAL_START_ID,
+    )
+)
+SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)
+
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    with open(tiktoken_bpe_file, "rb") as f:
+        contents = f.read()
+    return {
+        base64.b64decode(token): int(rank)
+        for token, rank in (line.split() for line in contents.splitlines() if line)
+    }
+
+
+class QWenTokenizer(PreTrainedTokenizer):
+    """QWen tokenizer."""
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    def __init__(
+        self,
+        vocab_file,
+        errors="replace",
+        extra_vocab_file=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        # how to handle errors in decoding UTF-8 byte sequences
+        # use ignore if you are in streaming inference
+        self.errors = errors  
+
+        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
+        self.special_tokens = {
+            token: index
+            for index, token in SPECIAL_TOKENS
+        }
+
+        # try load extra vocab from file
+        if extra_vocab_file is not None:
+            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
+            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
+            for token, index in extra_mergeable_ranks.items():
+                if token in self.mergeable_ranks:
+                    logger.info(f"extra token {token} exists, skipping")
+                    continue
+                if index in used_ids:
+                    logger.info(f'the index {index} for extra token {token} exists, skipping')
+                    continue
+                self.mergeable_ranks[token] = index
+            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this
+
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        assert (
+            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
+        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
+
+        self.decoder = {
+            v: k for k, v in self.mergeable_ranks.items()
+        }  # type: dict[int, bytes|str]
+        self.decoder.update({v: k for k, v in self.special_tokens.items()})
+
+        self.tokenizer = enc  # type: tiktoken.Encoding
+
+        self.eod_id = self.tokenizer.eot_token
+        self.im_start_id = self.special_tokens[IMSTART]
+        self.im_end_id = self.special_tokens[IMEND]
+
+    def __getstate__(self):
+        # for pickle lovers
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        # tokenizer is not python native; don't pass it; rebuild it
+        self.__dict__.update(state)
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        self.tokenizer = enc
+
+    def __len__(self) -> int:
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.special_tokens:
+                return self.special_tokens[tokens]
+            else:
+                return self.mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.special_tokens:
+                ids.append(self.special_tokens[token])
+            else:
+                ids.append(self.mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS_SET:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "qwen.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        if token in self.mergeable_ranks:
+            return self.mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.eod_id]
+        return self.tokenizer.decode(token_ids, errors=errors or self.errors)

LLM-Detector-V5-11w/checkpoint-21000/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 8192,
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "QWenTokenizer"
+}