Upload 12 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

MAP_EXP_12_FULL.py

@@ -0,0 +1,360 @@
+# All imports at the top
+import torch
+import shutil
+import numpy as np
+import pandas as pd
+import mlflow
+from collections import Counter
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder
+from datasets import Dataset
+from transformers import (
+    AutoTokenizer, 
+    TrainingArguments, 
+    Trainer, 
+    DataCollatorWithPadding,
+    BitsAndBytesConfig,
+    AutoModelForSequenceClassification
+)
+from peft import (
+    LoraConfig,
+    TaskType,
+    get_peft_model,
+    prepare_model_for_kbit_training,
+)
+
+# Configuration
+model_name = "Qwen/Qwen2.5-Math-7B"
+MAX_LEN = 256
+
+# MLflow setup
+mlflow.set_tracking_uri("http://127.0.0.1:8081")
+
+# Step 2: Loading the dataset
+
+le = LabelEncoder()
+train = pd.read_csv('train.csv')
+train.Misconception = train.Misconception.fillna('NA')
+train['target'] = train.Category +":"+ train.Misconception
+train['label'] = le.fit_transform(train['target'])
+n_classes = len(le.classes_)
+print(f"Train shape: {train.shape} with {n_classes} target classes")
+print(train.head())
+
+# Process correct answers
+idx = train.apply(lambda row: row.Category.split('_')[0], axis=1) == 'True'
+correct = train.loc[idx].copy()
+correct['c'] = correct.groupby(['QuestionId', 'MC_Answer']).MC_Answer.transform('count')
+correct = correct.sort_values('c', ascending=False)
+correct = correct.drop_duplicates(['QuestionId'])
+correct = correct[['QuestionId', 'MC_Answer']]
+correct['is_correct'] = 1
+
+train = train.merge(correct, on=['QuestionId', 'MC_Answer'], how='left')
+train.is_correct = train.is_correct.fillna(0)
+
+# Format input text
+def format_input(row):
+    x = "This answer is correct."
+    if not row['is_correct']:
+        x = "This is answer is incorrect."
+    return (
+        f"Question: {row['QuestionText']}\n"
+        f"Answer: {row['MC_Answer']}\n"
+        f"{x}\n"
+        f"Student Explanation: {row['StudentExplanation']}"
+    )
+
+train['text'] = train.apply(format_input, axis=1)
+
+# Split data
+train_df          = train
+#train_df, val_df = train_test_split(train, test_size=0.2, random_state=42)
+
+COLS = ['text', 'label']
+train_ds = Dataset.from_pandas(train_df[COLS])
+#val_ds = Dataset.from_pandas(val_df[COLS])
+
+# Initialize tokenizer
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Tokenization function
+def tokenize_func(example):
+    return tokenizer(
+        example["text"],
+        add_special_tokens=True,
+        truncation=True,
+        max_length=512,
+    )
+
+# Tokenize datasets
+train_ds = train_ds.map(tokenize_func, batched=True, desc="Tokenizing train data")
+#eval_ds = val_ds.map(tokenize_func, batched=True, desc="Tokenizing eval data")
+
+# Step 3: Load model
+# Model configuration
+model_kwargs = dict(
+    trust_remote_code=True,
+    torch_dtype=torch.float16
+)
+
+model_kwargs["quantization_config"] = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_compute_dtype="float16",
+)
+
+# Load model
+print(f"Loading model : {model_name}")
+model = AutoModelForSequenceClassification.from_pretrained(
+    model_name, use_cache=False, num_labels=n_classes, **model_kwargs
+)
+model.config.pad_token_id = tokenizer.pad_token_id
+
+# LoRA configuration
+lora_config = LoraConfig(
+    r=64,
+    lora_alpha=64,
+    target_modules="all-linear",
+    lora_dropout=0.05,
+    bias="none",
+    task_type=TaskType.SEQ_CLS,
+    modules_to_save=["score"],
+)
+
+# Prepare model for training
+model = prepare_model_for_kbit_training(model)
+model = get_peft_model(model, lora_config)
+model.print_trainable_parameters()
+
+# Custom evaluation metric
+def compute_multi_map(eval_pred, ks=[3, 5, 10]):
+    """
+    Computes MAP@k and a detailed rank distribution.
+    
+    This includes:
+    - Rank counts for rank 1, 2-3, and above 3.
+    - For rank groups 2-3 and above 3, it finds the top 3 most frequent
+      classes and calculates their average probability score.
+    """
+    # 1. Unpack logits and labels
+    logits, labels = eval_pred
+    labels = np.array(labels)
+
+    # 2. Convert logits to probabilities
+    # The `probs` array has shape: (num_samples, num_classes)
+    probs = torch.nn.functional.softmax(torch.tensor(logits), dim=-1).numpy()
+
+    # 3. Get top-k predictions
+    max_k = max(ks)
+    top_k_preds = np.argsort(-probs, axis=1)[:, :max_k]
+
+    # 4. Create a boolean match array
+    match_array = (top_k_preds == labels[:, None])
+
+    # 5. Compute MAP@k for each specified k
+    metrics = {}
+    for k in ks:
+        match_at_k = match_array[:, :k]
+        ranks = np.argmax(match_at_k, axis=1) + 1
+        has_match_at_k = np.any(match_at_k, axis=1)
+        scores = has_match_at_k * (1.0 / ranks)
+        metrics[f"map@{k}"] = np.mean(scores)
+
+    # 6. Calculate detailed rank position breakdown
+    ranks_with_indices = [np.where(row)[0] for row in match_array]
+    correct_ranks = np.array([r[0] + 1 if len(r) > 0 else max_k + 1 for r in ranks_with_indices])
+
+    total = labels.shape[0]
+    metrics["rank_1"] = np.sum(correct_ranks == 1)
+    metrics["rank_2_to_3"] = np.sum((correct_ranks >= 2) & (correct_ranks <= 3))
+    metrics["rank_above_3"] = np.sum((correct_ranks > 3) & (correct_ranks <= max_k))
+    metrics["no_match_in_top_k"] = np.sum(correct_ranks > max_k)
+    metrics["total"] = total
+
+    # 7. Find top 3 classes for rank groups and their average probability
+    
+    # --- For ranks 2 to 3 ---
+    # Create a boolean mask for samples in this rank group
+    rank_2_to_3_mask = (correct_ranks >= 2) & (correct_ranks <= 3)
+    # Get the true labels for these samples
+    rank_2_to_3_labels = labels[rank_2_to_3_mask]
+
+    if len(rank_2_to_3_labels) > 0:
+        top_classes = Counter(rank_2_to_3_labels).most_common(3)
+        augmented_top_classes = []
+        for cls, count in top_classes:
+            # Find samples that both belong to this class AND are in this rank group
+            class_in_group_mask = (labels == cls) & rank_2_to_3_mask
+            # Get the probabilities assigned to the correct class for these specific samples
+            class_probs = probs[class_in_group_mask, cls]
+            # Calculate the average probability and add to list
+            avg_prob = np.mean(class_probs)
+            augmented_top_classes.append((cls, count, round(float(avg_prob), 4)))
+        metrics["rank_2_to_3_details"] = augmented_top_classes
+    else:
+        metrics["rank_2_to_3_details"] = []
+
+    # --- For ranks above 3 (up to max_k) ---
+    rank_above_3_mask = (correct_ranks > 3) & (correct_ranks <= max_k)
+    rank_above_3_labels = labels[rank_above_3_mask]
+
+    if len(rank_above_3_labels) > 0:
+        top_classes = Counter(rank_above_3_labels).most_common(3)
+        augmented_top_classes = []
+        for cls, count in top_classes:
+            class_in_group_mask = (labels == cls) & rank_above_3_mask
+            class_probs = probs[class_in_group_mask, cls]
+            avg_prob = np.mean(class_probs)
+            augmented_top_classes.append((cls, count, round(float(avg_prob), 4)))
+        metrics["rank_above_3_details"] = augmented_top_classes
+    else:
+        metrics["rank_above_3_details"] = []
+
+    mlflow.log_metric("rank_1", metrics["rank_1"])
+    mlflow.log_metric("rank_2_to_3", metrics["rank_2_to_3"])
+    mlflow.log_metric("rank_above_3", metrics["rank_above_3"])
+    mlflow.log_metric("no_match_in_top_k", metrics["no_match_in_top_k"])
+    # mlflow.log_metric("rank_2_to_3_details", metrics["rank_2_to_3_details"])
+    # mlflow.log_metric("rank_above_3_details", metrics["rank_above_3_details"])
+
+    return metrics
+
+# Training arguments
+training_args = TrainingArguments(
+    output_dir="MAP_EXP_12_FULL",
+    eval_strategy="no",
+    save_strategy="no",
+    logging_strategy="steps",
+    #eval_steps=500,
+    logging_steps=100,
+    learning_rate=1e-4,
+    per_device_train_batch_size=16,
+    per_device_eval_batch_size=32,
+    gradient_accumulation_steps=1,
+    lr_scheduler_type="cosine",
+    warmup_ratio=0.05,
+    report_to="mlflow",
+    gradient_checkpointing=True,
+    group_by_length=True,
+    max_grad_norm=1.0,
+    weight_decay=0.01,
+    num_train_epochs=2
+)
+
+
+import torch
+import numpy as np
+import mlflow
+from collections import Counter
+from transformers import Trainer
+
+class MLflowMetricsLogger:
+    """
+    A callable class to compute and log metrics to MLflow with step tracking.
+    """
+    def __init__(self, trainer: Trainer, ks=[3, 5, 10]):
+        """
+        Initializes the metrics logger.
+        
+        Args:
+            trainer (Trainer): The Hugging Face Trainer instance.
+            ks (list): A list of k values for MAP@k calculation.
+        """
+        self.trainer = trainer
+        self.ks = ks
+
+    def __call__(self, eval_pred):
+        """
+        This method is called by the Trainer during evaluation.
+        """
+        # Get the current training step from the trainer's state
+        step = self.trainer.state.global_step
+
+        # 1. Unpack logits and labels
+        logits, labels = eval_pred
+        labels = np.array(labels)
+
+        # 2. Convert logits to probabilities
+        probs = torch.nn.functional.softmax(torch.tensor(logits), dim=-1).numpy()
+
+        # 3. Get top-k predictions
+        max_k = max(self.ks)
+        top_k_preds = np.argsort(-probs, axis=1)[:, :max_k]
+
+        # 4. Create a boolean match array
+        match_array = (top_k_preds == labels[:, None])
+
+        # 5. Compute MAP@k for each specified k
+        metrics = {}
+        for k in self.ks:
+            match_at_k = match_array[:, :k]
+            ranks = np.argmax(match_at_k, axis=1) + 1
+            has_match_at_k = np.any(match_at_k, axis=1)
+            scores = has_match_at_k * (1.0 / ranks)
+            metrics[f"map@{k}"] = np.mean(scores)
+
+        # 6. Calculate detailed rank position breakdown
+        ranks_with_indices = [np.where(row)[0] for row in match_array]
+        correct_ranks = np.array([r[0] + 1 if len(r) > 0 else max_k + 1 for r in ranks_with_indices])
+
+        total = labels.shape[0]
+        rank_1_count = np.sum(correct_ranks == 1)
+        rank_2_to_3_count = np.sum((correct_ranks >= 2) & (correct_ranks <= 3))
+        rank_above_3_count = np.sum((correct_ranks > 3) & (correct_ranks <= max_k))
+        no_match_count = np.sum(correct_ranks > max_k)
+
+        # Log metrics to MLflow WITH the step argument
+        mlflow.log_metric("rank_1", rank_1_count, step=step)
+        mlflow.log_metric("rank_2_to_3", rank_2_to_3_count, step=step)
+        mlflow.log_metric("rank_above_3", rank_above_3_count, step=step)
+        mlflow.log_metric("no_match_in_top_k", no_match_count, step=step)
+
+        # Note: The detailed lists cannot be logged as a time-series metric.
+        # These are better logged as artifacts (e.g., a JSON file) or a dictionary
+        # at the end of the run if needed.
+        # For example: mlflow.log_dict(details_dict, "rank_details.json")
+
+        # The Trainer still requires a dictionary of metrics to be returned.
+        metrics["rank_1"] = rank_1_count
+        metrics["rank_2_to_3"] = rank_2_to_3_count
+        metrics["rank_above_3"] = rank_above_3_count
+        metrics["no_match_in_top_k"] = no_match_count
+        metrics["total"] = total
+        
+        return metrics
+
+
+# Initialize trainer
+trainer = Trainer(
+    model,
+    args=training_args,
+    train_dataset=train_ds,
+    #eval_dataset=eval_ds,
+    tokenizer=tokenizer,
+    compute_metrics=compute_multi_map,
+    data_collator=DataCollatorWithPadding(tokenizer),
+)
+
+metrics_computer = MLflowMetricsLogger(trainer)
+
+# 3. Assign the instance to the trainer's compute_metrics attribute
+trainer.compute_metrics = metrics_computer
+
+# Main execution
+if __name__ == "__main__":
+    
+    # Start training
+    trainer.train()
+    
+    # Save the model
+    trainer.save_model("MAP_EXP_12_FULL")
+
+    source_file = "MAP_EXP_12_FULL.py"
+    destination_directory = "MAP_EXP_12_FULL"
+    
+    shutil.copy(source_file, destination_directory)
+    print(f"File '{source_file}' copied to '{destination_directory}'")
+    
+    print("Training completed and model saved!")

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Math-7B
+library_name: peft
+---
+
+# 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]
+- **Funded by [optional]:** [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 Dataset 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 Dataset 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]
+### Framework versions
+
+- PEFT 0.15.2

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Math-7B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0c3e10c4fa881e49c743e552df80019c7abc0946fd4e950e721b3c9bd87185
+size 646907648

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nPlease reason step by step, and put your final answer within \\boxed{}.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962b8d8c521fefa934665afddae177326e974ddd6a26e69ff31ad6bccbb5593b
+size 11421994

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ce2971b006c04a4aaa9d6cca5b69ec2690f637c52bc4f8589cd95f7217d92f
+size 5304