Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,9 @@ 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
+lora/sft-captcha/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lora/sft-captcha/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lora/sft-captcha/checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lora/sft-captcha/checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lora/sft-captcha/checkpoint-775/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lora/sft-captcha/tokenizer.json filter=lfs diff=lfs merge=lfs -text

lora/sft-captcha/README.md

@@ -0,0 +1,62 @@
+---
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-VL-4B-Instruct
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-4B-Instruct
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: sft-captcha
+  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. -->
+
+# sft-captcha
+
+This model is a fine-tuned version of [Qwen/Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct) on the new_dataset dataset.
+
+## 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: 8
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.6.0
+- Pytorch 2.5.1+cu121
+- Datasets 4.0.0
+- Tokenizers 0.22.2

lora/sft-captcha/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

lora/sft-captcha/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbbc568b3b10ea6e601db64bce50e3cdd551083e7288e2c8dd9d2d4220605219
+size 264316456

lora/sft-captcha/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 7.509104074275226e+17,
+    "train_loss": 0.31352297429115544,
+    "train_runtime": 25009.3076,
+    "train_samples_per_second": 0.99,
+    "train_steps_per_second": 0.031
+}

lora/sft-captcha/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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 %}

lora/sft-captcha/checkpoint-400/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-VL-4B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-4B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

lora/sft-captcha/checkpoint-400/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

lora/sft-captcha/checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66eeeee1ebad3f84ed03697a7cea74e5b0223bb59941d542f5bdc61e448335a
+size 264316456

lora/sft-captcha/checkpoint-400/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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 %}

lora/sft-captcha/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49df9d74c32cb35aab23ecd0094e6250cd5a11c35a06e201cb5136a52fd041ca
+size 528907898

lora/sft-captcha/checkpoint-400/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

lora/sft-captcha/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475fd467f417f0259650e7c80bd36d7eec27e4769fb5d99ba3ebaf101c351054
+size 14244

lora/sft-captcha/checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c801982aae9be06d302403c1fff693e53dedf89c1d3b689ee29fedad84a96d23
+size 988

lora/sft-captcha/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6555b29b300370c41c8532c7d7e8f3e8a569486e0856a98f852e0aafd33af3
+size 1064

lora/sft-captcha/checkpoint-400/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

lora/sft-captcha/checkpoint-400/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

lora/sft-captcha/checkpoint-400/trainer_state.json

@@ -0,0 +1,314 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.581583198707593,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06462035541195477,
+      "grad_norm": 2.068004846572876,
+      "learning_rate": 5.76923076923077e-06,
+      "loss": 0.9769228935241699,
+      "step": 10
+    },
+    {
+      "epoch": 0.12924071082390953,
+      "grad_norm": 0.9047558307647705,
+      "learning_rate": 1.217948717948718e-05,
+      "loss": 0.7594649791717529,
+      "step": 20
+    },
+    {
+      "epoch": 0.1938610662358643,
+      "grad_norm": 0.4503297805786133,
+      "learning_rate": 1.858974358974359e-05,
+      "loss": 0.5557493209838867,
+      "step": 30
+    },
+    {
+      "epoch": 0.25848142164781907,
+      "grad_norm": 0.37129801511764526,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4763153076171875,
+      "step": 40
+    },
+    {
+      "epoch": 0.32310177705977383,
+      "grad_norm": 0.2953853905200958,
+      "learning_rate": 3.141025641025641e-05,
+      "loss": 0.4166147708892822,
+      "step": 50
+    },
+    {
+      "epoch": 0.3877221324717286,
+      "grad_norm": 0.29160749912261963,
+      "learning_rate": 3.782051282051282e-05,
+      "loss": 0.3905663013458252,
+      "step": 60
+    },
+    {
+      "epoch": 0.45234248788368336,
+      "grad_norm": 0.27939939498901367,
+      "learning_rate": 4.423076923076923e-05,
+      "loss": 0.3649837732315063,
+      "step": 70
+    },
+    {
+      "epoch": 0.5169628432956381,
+      "grad_norm": 0.3130805492401123,
+      "learning_rate": 4.999974605277764e-05,
+      "loss": 0.3609442949295044,
+      "step": 80
+    },
+    {
+      "epoch": 0.5815831987075929,
+      "grad_norm": 0.3720378577709198,
+      "learning_rate": 4.996927862815294e-05,
+      "loss": 0.3543627977371216,
+      "step": 90
+    },
+    {
+      "epoch": 0.6462035541195477,
+      "grad_norm": 0.2810651361942291,
+      "learning_rate": 4.988809267347141e-05,
+      "loss": 0.345255446434021,
+      "step": 100
+    },
+    {
+      "epoch": 0.7108239095315024,
+      "grad_norm": 0.3126155734062195,
+      "learning_rate": 4.975635309667227e-05,
+      "loss": 0.33807756900787356,
+      "step": 110
+    },
+    {
+      "epoch": 0.7754442649434572,
+      "grad_norm": 0.3109033703804016,
+      "learning_rate": 4.957432749209755e-05,
+      "loss": 0.3394132614135742,
+      "step": 120
+    },
+    {
+      "epoch": 0.840064620355412,
+      "grad_norm": 0.3006167411804199,
+      "learning_rate": 4.934238559694448e-05,
+      "loss": 0.3244359016418457,
+      "step": 130
+    },
+    {
+      "epoch": 0.9046849757673667,
+      "grad_norm": 0.3104219138622284,
+      "learning_rate": 4.90609985402415e-05,
+      "loss": 0.3221057176589966,
+      "step": 140
+    },
+    {
+      "epoch": 0.9693053311793215,
+      "grad_norm": 0.330458402633667,
+      "learning_rate": 4.873073788587338e-05,
+      "loss": 0.3329624176025391,
+      "step": 150
+    },
+    {
+      "epoch": 1.0323101777059773,
+      "grad_norm": 0.2666167616844177,
+      "learning_rate": 4.835227447159939e-05,
+      "loss": 0.3191133737564087,
+      "step": 160
+    },
+    {
+      "epoch": 1.0969305331179322,
+      "grad_norm": 0.3217558264732361,
+      "learning_rate": 4.7926377046422575e-05,
+      "loss": 0.3055490255355835,
+      "step": 170
+    },
+    {
+      "epoch": 1.1615508885298869,
+      "grad_norm": 0.31330329179763794,
+      "learning_rate": 4.7453910709078145e-05,
+      "loss": 0.31946792602539065,
+      "step": 180
+    },
+    {
+      "epoch": 1.2261712439418417,
+      "grad_norm": 0.3254242539405823,
+      "learning_rate": 4.69358351508126e-05,
+      "loss": 0.3053389549255371,
+      "step": 190
+    },
+    {
+      "epoch": 1.2907915993537964,
+      "grad_norm": 0.3096122145652771,
+      "learning_rate": 4.637320270602314e-05,
+      "loss": 0.30810558795928955,
+      "step": 200
+    },
+    {
+      "epoch": 1.3554119547657513,
+      "grad_norm": 0.30546557903289795,
+      "learning_rate": 4.576715621471678e-05,
+      "loss": 0.31534519195556643,
+      "step": 210
+    },
+    {
+      "epoch": 1.420032310177706,
+      "grad_norm": 0.32512548565864563,
+      "learning_rate": 4.511892670113104e-05,
+      "loss": 0.3046459913253784,
+      "step": 220
+    },
+    {
+      "epoch": 1.4846526655896608,
+      "grad_norm": 0.32627010345458984,
+      "learning_rate": 4.442983087323167e-05,
+      "loss": 0.2983341455459595,
+      "step": 230
+    },
+    {
+      "epoch": 1.5492730210016155,
+      "grad_norm": 0.3522598147392273,
+      "learning_rate": 4.370126844816628e-05,
+      "loss": 0.3133318185806274,
+      "step": 240
+    },
+    {
+      "epoch": 1.6138933764135701,
+      "grad_norm": 0.30818620324134827,
+      "learning_rate": 4.293471930910668e-05,
+      "loss": 0.30533685684204104,
+      "step": 250
+    },
+    {
+      "epoch": 1.678513731825525,
+      "grad_norm": 0.2774396538734436,
+      "learning_rate": 4.213174049925498e-05,
+      "loss": 0.2984048843383789,
+      "step": 260
+    },
+    {
+      "epoch": 1.7431340872374799,
+      "grad_norm": 0.2943349778652191,
+      "learning_rate": 4.129396305911934e-05,
+      "loss": 0.2998037338256836,
+      "step": 270
+    },
+    {
+      "epoch": 1.8077544426494345,
+      "grad_norm": 0.30737221240997314,
+      "learning_rate": 4.042308871348371e-05,
+      "loss": 0.3016969680786133,
+      "step": 280
+    },
+    {
+      "epoch": 1.8723747980613892,
+      "grad_norm": 0.3105849325656891,
+      "learning_rate": 3.9520886414800936e-05,
+      "loss": 0.3014758348464966,
+      "step": 290
+    },
+    {
+      "epoch": 1.936995153473344,
+      "grad_norm": 0.29112061858177185,
+      "learning_rate": 3.858918875003053e-05,
+      "loss": 0.297167444229126,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3953491747379303,
+      "learning_rate": 3.7629888218219774e-05,
+      "loss": 0.29504544734954835,
+      "step": 310
+    },
+    {
+      "epoch": 2.0646203554119547,
+      "grad_norm": 0.29763659834861755,
+      "learning_rate": 3.664493338638898e-05,
+      "loss": 0.28955745697021484,
+      "step": 320
+    },
+    {
+      "epoch": 2.1292407108239093,
+      "grad_norm": 0.3380239009857178,
+      "learning_rate": 3.5636324931529554e-05,
+      "loss": 0.28567984104156496,
+      "step": 330
+    },
+    {
+      "epoch": 2.1938610662358644,
+      "grad_norm": 0.31489691138267517,
+      "learning_rate": 3.46061115767542e-05,
+      "loss": 0.28932580947875974,
+      "step": 340
+    },
+    {
+      "epoch": 2.258481421647819,
+      "grad_norm": 0.3106003403663635,
+      "learning_rate": 3.3556385929854164e-05,
+      "loss": 0.2879155158996582,
+      "step": 350
+    },
+    {
+      "epoch": 2.3231017770597737,
+      "grad_norm": 0.2789410948753357,
+      "learning_rate": 3.248928023271624e-05,
+      "loss": 0.2938661813735962,
+      "step": 360
+    },
+    {
+      "epoch": 2.387722132471729,
+      "grad_norm": 0.2844054102897644,
+      "learning_rate": 3.140696203023348e-05,
+      "loss": 0.2907016515731812,
+      "step": 370
+    },
+    {
+      "epoch": 2.4523424878836835,
+      "grad_norm": 0.3297322392463684,
+      "learning_rate": 3.0311629767507232e-05,
+      "loss": 0.28118228912353516,
+      "step": 380
+    },
+    {
+      "epoch": 2.516962843295638,
+      "grad_norm": 0.30098527669906616,
+      "learning_rate": 2.920550832428337e-05,
+      "loss": 0.2846884489059448,
+      "step": 390
+    },
+    {
+      "epoch": 2.581583198707593,
+      "grad_norm": 0.31197914481163025,
+      "learning_rate": 2.809084449569365e-05,
+      "loss": 0.28516063690185545,
+      "step": 400
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 775,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.876922101492941e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

lora/sft-captcha/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994239c83a21a412f370376b6709e6af83b0c60df0ba98c0dc5d4b0c9b6306e1
+size 5496

lora/sft-captcha/checkpoint-500/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-VL-4B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-4B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

lora/sft-captcha/checkpoint-500/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

lora/sft-captcha/checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f24bc5bebdaf93e8b3a102055eef9253fc374041639654ee6cc5cb8caa6961b
+size 264316456

lora/sft-captcha/checkpoint-500/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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 %}

lora/sft-captcha/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959218718c23668aca16b7c6e08b83540dc806dc9b120b61a8f4d51851d4b54c
+size 528907898

lora/sft-captcha/checkpoint-500/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

lora/sft-captcha/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d1aab3d1e368c6691900c295360091c6e7e65e662b8d111e42b019a91efaf2
+size 14244

lora/sft-captcha/checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18b984273ea2d45b7ffb1d047bb359d93111e41fcad70d16a1b453fd38f72636
+size 988

lora/sft-captcha/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9a07f637a01e092d5d5626103dd0ebc2ecea11a83d0124a7099d655e090b6b
+size 1064

lora/sft-captcha/checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

lora/sft-captcha/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

lora/sft-captcha/checkpoint-500/trainer_state.json

@@ -0,0 +1,384 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.2261712439418417,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06462035541195477,
+      "grad_norm": 2.068004846572876,
+      "learning_rate": 5.76923076923077e-06,
+      "loss": 0.9769228935241699,
+      "step": 10
+    },
+    {
+      "epoch": 0.12924071082390953,
+      "grad_norm": 0.9047558307647705,
+      "learning_rate": 1.217948717948718e-05,
+      "loss": 0.7594649791717529,
+      "step": 20
+    },
+    {
+      "epoch": 0.1938610662358643,
+      "grad_norm": 0.4503297805786133,
+      "learning_rate": 1.858974358974359e-05,
+      "loss": 0.5557493209838867,
+      "step": 30
+    },
+    {
+      "epoch": 0.25848142164781907,
+      "grad_norm": 0.37129801511764526,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4763153076171875,
+      "step": 40
+    },
+    {
+      "epoch": 0.32310177705977383,
+      "grad_norm": 0.2953853905200958,
+      "learning_rate": 3.141025641025641e-05,
+      "loss": 0.4166147708892822,
+      "step": 50
+    },
+    {
+      "epoch": 0.3877221324717286,
+      "grad_norm": 0.29160749912261963,
+      "learning_rate": 3.782051282051282e-05,
+      "loss": 0.3905663013458252,
+      "step": 60
+    },
+    {
+      "epoch": 0.45234248788368336,
+      "grad_norm": 0.27939939498901367,
+      "learning_rate": 4.423076923076923e-05,
+      "loss": 0.3649837732315063,
+      "step": 70
+    },
+    {
+      "epoch": 0.5169628432956381,
+      "grad_norm": 0.3130805492401123,
+      "learning_rate": 4.999974605277764e-05,
+      "loss": 0.3609442949295044,
+      "step": 80
+    },
+    {
+      "epoch": 0.5815831987075929,
+      "grad_norm": 0.3720378577709198,
+      "learning_rate": 4.996927862815294e-05,
+      "loss": 0.3543627977371216,
+      "step": 90
+    },
+    {
+      "epoch": 0.6462035541195477,
+      "grad_norm": 0.2810651361942291,
+      "learning_rate": 4.988809267347141e-05,
+      "loss": 0.345255446434021,
+      "step": 100
+    },
+    {
+      "epoch": 0.7108239095315024,
+      "grad_norm": 0.3126155734062195,
+      "learning_rate": 4.975635309667227e-05,
+      "loss": 0.33807756900787356,
+      "step": 110
+    },
+    {
+      "epoch": 0.7754442649434572,
+      "grad_norm": 0.3109033703804016,
+      "learning_rate": 4.957432749209755e-05,
+      "loss": 0.3394132614135742,
+      "step": 120
+    },
+    {
+      "epoch": 0.840064620355412,
+      "grad_norm": 0.3006167411804199,
+      "learning_rate": 4.934238559694448e-05,
+      "loss": 0.3244359016418457,
+      "step": 130
+    },
+    {
+      "epoch": 0.9046849757673667,
+      "grad_norm": 0.3104219138622284,
+      "learning_rate": 4.90609985402415e-05,
+      "loss": 0.3221057176589966,
+      "step": 140
+    },
+    {
+      "epoch": 0.9693053311793215,
+      "grad_norm": 0.330458402633667,
+      "learning_rate": 4.873073788587338e-05,
+      "loss": 0.3329624176025391,
+      "step": 150
+    },
+    {
+      "epoch": 1.0323101777059773,
+      "grad_norm": 0.2666167616844177,
+      "learning_rate": 4.835227447159939e-05,
+      "loss": 0.3191133737564087,
+      "step": 160
+    },
+    {
+      "epoch": 1.0969305331179322,
+      "grad_norm": 0.3217558264732361,
+      "learning_rate": 4.7926377046422575e-05,
+      "loss": 0.3055490255355835,
+      "step": 170
+    },
+    {
+      "epoch": 1.1615508885298869,
+      "grad_norm": 0.31330329179763794,
+      "learning_rate": 4.7453910709078145e-05,
+      "loss": 0.31946792602539065,
+      "step": 180
+    },
+    {
+      "epoch": 1.2261712439418417,
+      "grad_norm": 0.3254242539405823,
+      "learning_rate": 4.69358351508126e-05,
+      "loss": 0.3053389549255371,
+      "step": 190
+    },
+    {
+      "epoch": 1.2907915993537964,
+      "grad_norm": 0.3096122145652771,
+      "learning_rate": 4.637320270602314e-05,
+      "loss": 0.30810558795928955,
+      "step": 200
+    },
+    {
+      "epoch": 1.3554119547657513,
+      "grad_norm": 0.30546557903289795,
+      "learning_rate": 4.576715621471678e-05,
+      "loss": 0.31534519195556643,
+      "step": 210
+    },
+    {
+      "epoch": 1.420032310177706,
+      "grad_norm": 0.32512548565864563,
+      "learning_rate": 4.511892670113104e-05,
+      "loss": 0.3046459913253784,
+      "step": 220
+    },
+    {
+      "epoch": 1.4846526655896608,
+      "grad_norm": 0.32627010345458984,
+      "learning_rate": 4.442983087323167e-05,
+      "loss": 0.2983341455459595,
+      "step": 230
+    },
+    {
+      "epoch": 1.5492730210016155,
+      "grad_norm": 0.3522598147392273,
+      "learning_rate": 4.370126844816628e-05,
+      "loss": 0.3133318185806274,
+      "step": 240
+    },
+    {
+      "epoch": 1.6138933764135701,
+      "grad_norm": 0.30818620324134827,
+      "learning_rate": 4.293471930910668e-05,
+      "loss": 0.30533685684204104,
+      "step": 250
+    },
+    {
+      "epoch": 1.678513731825525,
+      "grad_norm": 0.2774396538734436,
+      "learning_rate": 4.213174049925498e-05,
+      "loss": 0.2984048843383789,
+      "step": 260
+    },
+    {
+      "epoch": 1.7431340872374799,
+      "grad_norm": 0.2943349778652191,
+      "learning_rate": 4.129396305911934e-05,
+      "loss": 0.2998037338256836,
+      "step": 270
+    },
+    {
+      "epoch": 1.8077544426494345,
+      "grad_norm": 0.30737221240997314,
+      "learning_rate": 4.042308871348371e-05,
+      "loss": 0.3016969680786133,
+      "step": 280
+    },
+    {
+      "epoch": 1.8723747980613892,
+      "grad_norm": 0.3105849325656891,
+      "learning_rate": 3.9520886414800936e-05,
+      "loss": 0.3014758348464966,
+      "step": 290
+    },
+    {
+      "epoch": 1.936995153473344,
+      "grad_norm": 0.29112061858177185,
+      "learning_rate": 3.858918875003053e-05,
+      "loss": 0.297167444229126,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3953491747379303,
+      "learning_rate": 3.7629888218219774e-05,
+      "loss": 0.29504544734954835,
+      "step": 310
+    },
+    {
+      "epoch": 2.0646203554119547,
+      "grad_norm": 0.29763659834861755,
+      "learning_rate": 3.664493338638898e-05,
+      "loss": 0.28955745697021484,
+      "step": 320
+    },
+    {
+      "epoch": 2.1292407108239093,
+      "grad_norm": 0.3380239009857178,
+      "learning_rate": 3.5636324931529554e-05,
+      "loss": 0.28567984104156496,
+      "step": 330
+    },
+    {
+      "epoch": 2.1938610662358644,
+      "grad_norm": 0.31489691138267517,
+      "learning_rate": 3.46061115767542e-05,
+      "loss": 0.28932580947875974,
+      "step": 340
+    },
+    {
+      "epoch": 2.258481421647819,
+      "grad_norm": 0.3106003403663635,
+      "learning_rate": 3.3556385929854164e-05,
+      "loss": 0.2879155158996582,
+      "step": 350
+    },
+    {
+      "epoch": 2.3231017770597737,
+      "grad_norm": 0.2789410948753357,
+      "learning_rate": 3.248928023271624e-05,
+      "loss": 0.2938661813735962,
+      "step": 360
+    },
+    {
+      "epoch": 2.387722132471729,
+      "grad_norm": 0.2844054102897644,
+      "learning_rate": 3.140696203023348e-05,
+      "loss": 0.2907016515731812,
+      "step": 370
+    },
+    {
+      "epoch": 2.4523424878836835,
+      "grad_norm": 0.3297322392463684,
+      "learning_rate": 3.0311629767507232e-05,
+      "loss": 0.28118228912353516,
+      "step": 380
+    },
+    {
+      "epoch": 2.516962843295638,
+      "grad_norm": 0.30098527669906616,
+      "learning_rate": 2.920550832428337e-05,
+      "loss": 0.2846884489059448,
+      "step": 390
+    },
+    {
+      "epoch": 2.581583198707593,
+      "grad_norm": 0.31197914481163025,
+      "learning_rate": 2.809084449569365e-05,
+      "loss": 0.28516063690185545,
+      "step": 400
+    },
+    {
+      "epoch": 2.6462035541195474,
+      "grad_norm": 0.30557820200920105,
+      "learning_rate": 2.6969902428481557e-05,
+      "loss": 0.2813657283782959,
+      "step": 410
+    },
+    {
+      "epoch": 2.7108239095315025,
+      "grad_norm": 0.3514881730079651,
+      "learning_rate": 2.584495902198307e-05,
+      "loss": 0.2873976469039917,
+      "step": 420
+    },
+    {
+      "epoch": 2.775444264943457,
+      "grad_norm": 0.3010100722312927,
+      "learning_rate": 2.4718299303203742e-05,
+      "loss": 0.2792309045791626,
+      "step": 430
+    },
+    {
+      "epoch": 2.840064620355412,
+      "grad_norm": 0.33192241191864014,
+      "learning_rate": 2.3592211785386642e-05,
+      "loss": 0.2784327745437622,
+      "step": 440
+    },
+    {
+      "epoch": 2.904684975767367,
+      "grad_norm": 0.3093332350254059,
+      "learning_rate": 2.246898381949894e-05,
+      "loss": 0.28588788509368895,
+      "step": 450
+    },
+    {
+      "epoch": 2.9693053311793216,
+      "grad_norm": 0.33140891790390015,
+      "learning_rate": 2.1350896948079226e-05,
+      "loss": 0.2833216428756714,
+      "step": 460
+    },
+    {
+      "epoch": 3.0323101777059773,
+      "grad_norm": 0.31609705090522766,
+      "learning_rate": 2.0240222270883288e-05,
+      "loss": 0.28030478954315186,
+      "step": 470
+    },
+    {
+      "epoch": 3.096930533117932,
+      "grad_norm": 0.2810538113117218,
+      "learning_rate": 1.913921583174154e-05,
+      "loss": 0.27578275203704833,
+      "step": 480
+    },
+    {
+      "epoch": 3.161550888529887,
+      "grad_norm": 0.3165380358695984,
+      "learning_rate": 1.805011403599862e-05,
+      "loss": 0.27012245655059813,
+      "step": 490
+    },
+    {
+      "epoch": 3.2261712439418417,
+      "grad_norm": 0.3220997452735901,
+      "learning_rate": 1.697512910784352e-05,
+      "loss": 0.2735466957092285,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 775,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.8452189110984704e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

lora/sft-captcha/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994239c83a21a412f370376b6709e6af83b0c60df0ba98c0dc5d4b0c9b6306e1
+size 5496

lora/sft-captcha/checkpoint-600/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-VL-4B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-4B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

lora/sft-captcha/checkpoint-600/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

lora/sft-captcha/checkpoint-600/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a5721f058d1fe20172472aa0fe233c7960f2fedeed5f13f328b9ad96c0d00b7
+size 264316456

lora/sft-captcha/checkpoint-600/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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 %}

lora/sft-captcha/checkpoint-600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d534d1b2f938995e792afddf132a3a16a82d8dc8544391a789fcd4f471f78053
+size 528907898

lora/sft-captcha/checkpoint-600/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

lora/sft-captcha/checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f541f824f68fa5ee039423d4bc10b573113d8ccb48fb258d6b1fda9dace15c4
+size 14244

lora/sft-captcha/checkpoint-600/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e32b8db4f4cba2b7b0157ab60a064591c3802a9067529d5fddbb1c6c1e99660b
+size 988

lora/sft-captcha/checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74e2a2ae06cc083da5b0fbf7843ecfcacdb4293c8a4f47b648e760b6dddaad8
+size 1064

lora/sft-captcha/checkpoint-600/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

lora/sft-captcha/checkpoint-600/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

lora/sft-captcha/checkpoint-600/trainer_state.json

@@ -0,0 +1,454 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.872374798061389,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06462035541195477,
+      "grad_norm": 2.068004846572876,
+      "learning_rate": 5.76923076923077e-06,
+      "loss": 0.9769228935241699,
+      "step": 10
+    },
+    {
+      "epoch": 0.12924071082390953,
+      "grad_norm": 0.9047558307647705,
+      "learning_rate": 1.217948717948718e-05,
+      "loss": 0.7594649791717529,
+      "step": 20
+    },
+    {
+      "epoch": 0.1938610662358643,
+      "grad_norm": 0.4503297805786133,
+      "learning_rate": 1.858974358974359e-05,
+      "loss": 0.5557493209838867,
+      "step": 30
+    },
+    {
+      "epoch": 0.25848142164781907,
+      "grad_norm": 0.37129801511764526,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4763153076171875,
+      "step": 40
+    },
+    {
+      "epoch": 0.32310177705977383,
+      "grad_norm": 0.2953853905200958,
+      "learning_rate": 3.141025641025641e-05,
+      "loss": 0.4166147708892822,
+      "step": 50
+    },
+    {
+      "epoch": 0.3877221324717286,
+      "grad_norm": 0.29160749912261963,
+      "learning_rate": 3.782051282051282e-05,
+      "loss": 0.3905663013458252,
+      "step": 60
+    },
+    {
+      "epoch": 0.45234248788368336,
+      "grad_norm": 0.27939939498901367,
+      "learning_rate": 4.423076923076923e-05,
+      "loss": 0.3649837732315063,
+      "step": 70
+    },
+    {
+      "epoch": 0.5169628432956381,
+      "grad_norm": 0.3130805492401123,
+      "learning_rate": 4.999974605277764e-05,
+      "loss": 0.3609442949295044,
+      "step": 80
+    },
+    {
+      "epoch": 0.5815831987075929,
+      "grad_norm": 0.3720378577709198,
+      "learning_rate": 4.996927862815294e-05,
+      "loss": 0.3543627977371216,
+      "step": 90
+    },
+    {
+      "epoch": 0.6462035541195477,
+      "grad_norm": 0.2810651361942291,
+      "learning_rate": 4.988809267347141e-05,
+      "loss": 0.345255446434021,
+      "step": 100
+    },
+    {
+      "epoch": 0.7108239095315024,
+      "grad_norm": 0.3126155734062195,
+      "learning_rate": 4.975635309667227e-05,
+      "loss": 0.33807756900787356,
+      "step": 110
+    },
+    {
+      "epoch": 0.7754442649434572,
+      "grad_norm": 0.3109033703804016,
+      "learning_rate": 4.957432749209755e-05,
+      "loss": 0.3394132614135742,
+      "step": 120
+    },
+    {
+      "epoch": 0.840064620355412,
+      "grad_norm": 0.3006167411804199,
+      "learning_rate": 4.934238559694448e-05,
+      "loss": 0.3244359016418457,
+      "step": 130
+    },
+    {
+      "epoch": 0.9046849757673667,
+      "grad_norm": 0.3104219138622284,
+      "learning_rate": 4.90609985402415e-05,
+      "loss": 0.3221057176589966,
+      "step": 140
+    },
+    {
+      "epoch": 0.9693053311793215,
+      "grad_norm": 0.330458402633667,
+      "learning_rate": 4.873073788587338e-05,
+      "loss": 0.3329624176025391,
+      "step": 150
+    },
+    {
+      "epoch": 1.0323101777059773,
+      "grad_norm": 0.2666167616844177,
+      "learning_rate": 4.835227447159939e-05,
+      "loss": 0.3191133737564087,
+      "step": 160
+    },
+    {
+      "epoch": 1.0969305331179322,
+      "grad_norm": 0.3217558264732361,
+      "learning_rate": 4.7926377046422575e-05,
+      "loss": 0.3055490255355835,
+      "step": 170
+    },
+    {
+      "epoch": 1.1615508885298869,
+      "grad_norm": 0.31330329179763794,
+      "learning_rate": 4.7453910709078145e-05,
+      "loss": 0.31946792602539065,
+      "step": 180
+    },
+    {
+      "epoch": 1.2261712439418417,
+      "grad_norm": 0.3254242539405823,
+      "learning_rate": 4.69358351508126e-05,
+      "loss": 0.3053389549255371,
+      "step": 190
+    },
+    {
+      "epoch": 1.2907915993537964,
+      "grad_norm": 0.3096122145652771,
+      "learning_rate": 4.637320270602314e-05,
+      "loss": 0.30810558795928955,
+      "step": 200
+    },
+    {
+      "epoch": 1.3554119547657513,
+      "grad_norm": 0.30546557903289795,
+      "learning_rate": 4.576715621471678e-05,
+      "loss": 0.31534519195556643,
+      "step": 210
+    },
+    {
+      "epoch": 1.420032310177706,
+      "grad_norm": 0.32512548565864563,
+      "learning_rate": 4.511892670113104e-05,
+      "loss": 0.3046459913253784,
+      "step": 220
+    },
+    {
+      "epoch": 1.4846526655896608,
+      "grad_norm": 0.32627010345458984,
+      "learning_rate": 4.442983087323167e-05,
+      "loss": 0.2983341455459595,
+      "step": 230
+    },
+    {
+      "epoch": 1.5492730210016155,
+      "grad_norm": 0.3522598147392273,
+      "learning_rate": 4.370126844816628e-05,
+      "loss": 0.3133318185806274,
+      "step": 240
+    },
+    {
+      "epoch": 1.6138933764135701,
+      "grad_norm": 0.30818620324134827,
+      "learning_rate": 4.293471930910668e-05,
+      "loss": 0.30533685684204104,
+      "step": 250
+    },
+    {
+      "epoch": 1.678513731825525,
+      "grad_norm": 0.2774396538734436,
+      "learning_rate": 4.213174049925498e-05,
+      "loss": 0.2984048843383789,
+      "step": 260
+    },
+    {
+      "epoch": 1.7431340872374799,
+      "grad_norm": 0.2943349778652191,
+      "learning_rate": 4.129396305911934e-05,
+      "loss": 0.2998037338256836,
+      "step": 270
+    },
+    {
+      "epoch": 1.8077544426494345,
+      "grad_norm": 0.30737221240997314,
+      "learning_rate": 4.042308871348371e-05,
+      "loss": 0.3016969680786133,
+      "step": 280
+    },
+    {
+      "epoch": 1.8723747980613892,
+      "grad_norm": 0.3105849325656891,
+      "learning_rate": 3.9520886414800936e-05,
+      "loss": 0.3014758348464966,
+      "step": 290
+    },
+    {
+      "epoch": 1.936995153473344,
+      "grad_norm": 0.29112061858177185,
+      "learning_rate": 3.858918875003053e-05,
+      "loss": 0.297167444229126,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3953491747379303,
+      "learning_rate": 3.7629888218219774e-05,
+      "loss": 0.29504544734954835,
+      "step": 310
+    },
+    {
+      "epoch": 2.0646203554119547,
+      "grad_norm": 0.29763659834861755,
+      "learning_rate": 3.664493338638898e-05,
+      "loss": 0.28955745697021484,
+      "step": 320
+    },
+    {
+      "epoch": 2.1292407108239093,
+      "grad_norm": 0.3380239009857178,
+      "learning_rate": 3.5636324931529554e-05,
+      "loss": 0.28567984104156496,
+      "step": 330
+    },
+    {
+      "epoch": 2.1938610662358644,
+      "grad_norm": 0.31489691138267517,
+      "learning_rate": 3.46061115767542e-05,
+      "loss": 0.28932580947875974,
+      "step": 340
+    },
+    {
+      "epoch": 2.258481421647819,
+      "grad_norm": 0.3106003403663635,
+      "learning_rate": 3.3556385929854164e-05,
+      "loss": 0.2879155158996582,
+      "step": 350
+    },
+    {
+      "epoch": 2.3231017770597737,
+      "grad_norm": 0.2789410948753357,
+      "learning_rate": 3.248928023271624e-05,
+      "loss": 0.2938661813735962,
+      "step": 360
+    },
+    {
+      "epoch": 2.387722132471729,
+      "grad_norm": 0.2844054102897644,
+      "learning_rate": 3.140696203023348e-05,
+      "loss": 0.2907016515731812,
+      "step": 370
+    },
+    {
+      "epoch": 2.4523424878836835,
+      "grad_norm": 0.3297322392463684,
+      "learning_rate": 3.0311629767507232e-05,
+      "loss": 0.28118228912353516,
+      "step": 380
+    },
+    {
+      "epoch": 2.516962843295638,
+      "grad_norm": 0.30098527669906616,
+      "learning_rate": 2.920550832428337e-05,
+      "loss": 0.2846884489059448,
+      "step": 390
+    },
+    {
+      "epoch": 2.581583198707593,
+      "grad_norm": 0.31197914481163025,
+      "learning_rate": 2.809084449569365e-05,
+      "loss": 0.28516063690185545,
+      "step": 400
+    },
+    {
+      "epoch": 2.6462035541195474,
+      "grad_norm": 0.30557820200920105,
+      "learning_rate": 2.6969902428481557e-05,
+      "loss": 0.2813657283782959,
+      "step": 410
+    },
+    {
+      "epoch": 2.7108239095315025,
+      "grad_norm": 0.3514881730079651,
+      "learning_rate": 2.584495902198307e-05,
+      "loss": 0.2873976469039917,
+      "step": 420
+    },
+    {
+      "epoch": 2.775444264943457,
+      "grad_norm": 0.3010100722312927,
+      "learning_rate": 2.4718299303203742e-05,
+      "loss": 0.2792309045791626,
+      "step": 430
+    },
+    {
+      "epoch": 2.840064620355412,
+      "grad_norm": 0.33192241191864014,
+      "learning_rate": 2.3592211785386642e-05,
+      "loss": 0.2784327745437622,
+      "step": 440
+    },
+    {
+      "epoch": 2.904684975767367,
+      "grad_norm": 0.3093332350254059,
+      "learning_rate": 2.246898381949894e-05,
+      "loss": 0.28588788509368895,
+      "step": 450
+    },
+    {
+      "epoch": 2.9693053311793216,
+      "grad_norm": 0.33140891790390015,
+      "learning_rate": 2.1350896948079226e-05,
+      "loss": 0.2833216428756714,
+      "step": 460
+    },
+    {
+      "epoch": 3.0323101777059773,
+      "grad_norm": 0.31609705090522766,
+      "learning_rate": 2.0240222270883288e-05,
+      "loss": 0.28030478954315186,
+      "step": 470
+    },
+    {
+      "epoch": 3.096930533117932,
+      "grad_norm": 0.2810538113117218,
+      "learning_rate": 1.913921583174154e-05,
+      "loss": 0.27578275203704833,
+      "step": 480
+    },
+    {
+      "epoch": 3.161550888529887,
+      "grad_norm": 0.3165380358695984,
+      "learning_rate": 1.805011403599862e-05,
+      "loss": 0.27012245655059813,
+      "step": 490
+    },
+    {
+      "epoch": 3.2261712439418417,
+      "grad_norm": 0.3220997452735901,
+      "learning_rate": 1.697512910784352e-05,
+      "loss": 0.2735466957092285,
+      "step": 500
+    },
+    {
+      "epoch": 3.2907915993537964,
+      "grad_norm": 0.3499109447002411,
+      "learning_rate": 1.5916444596757218e-05,
+      "loss": 0.27160613536834716,
+      "step": 510
+    },
+    {
+      "epoch": 3.355411954765751,
+      "grad_norm": 0.3451310694217682,
+      "learning_rate": 1.4876210942205604e-05,
+      "loss": 0.27280707359313966,
+      "step": 520
+    },
+    {
+      "epoch": 3.420032310177706,
+      "grad_norm": 0.33574041724205017,
+      "learning_rate": 1.3856541105586545e-05,
+      "loss": 0.27128801345825193,
+      "step": 530
+    },
+    {
+      "epoch": 3.484652665589661,
+      "grad_norm": 0.3565731346607208,
+      "learning_rate": 1.2859506278303979e-05,
+      "loss": 0.2736222743988037,
+      "step": 540
+    },
+    {
+      "epoch": 3.5492730210016155,
+      "grad_norm": 0.32914265990257263,
+      "learning_rate": 1.1887131674686596e-05,
+      "loss": 0.27256240844726565,
+      "step": 550
+    },
+    {
+      "epoch": 3.61389337641357,
+      "grad_norm": 0.31808099150657654,
+      "learning_rate": 1.0941392418297026e-05,
+      "loss": 0.27215673923492434,
+      "step": 560
+    },
+    {
+      "epoch": 3.678513731825525,
+      "grad_norm": 0.3377521336078644,
+      "learning_rate": 1.0024209529987149e-05,
+      "loss": 0.2722803592681885,
+      "step": 570
+    },
+    {
+      "epoch": 3.74313408723748,
+      "grad_norm": 0.33442333340644836,
+      "learning_rate": 9.137446025848914e-06,
+      "loss": 0.27033517360687254,
+      "step": 580
+    },
+    {
+      "epoch": 3.8077544426494345,
+      "grad_norm": 0.32362648844718933,
+      "learning_rate": 8.282903132986526e-06,
+      "loss": 0.268932580947876,
+      "step": 590
+    },
+    {
+      "epoch": 3.872374798061389,
+      "grad_norm": 0.33127161860466003,
+      "learning_rate": 7.462316630796834e-06,
+      "loss": 0.274311900138855,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 775,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.816662323100877e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

lora/sft-captcha/checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994239c83a21a412f370376b6709e6af83b0c60df0ba98c0dc5d4b0c9b6306e1
+size 5496

lora/sft-captcha/checkpoint-700/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-VL-4B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-VL-4B-Instruct
+- llama-factory
+- lora
+- transformers
+---
+
+# 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 0.18.1

lora/sft-captcha/checkpoint-700/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-VL-4B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

lora/sft-captcha/checkpoint-700/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:307c2b4e2255090e13237967266449a5f71c8de87aa3403c0e0a4db1b76359cf
+size 264316456

lora/sft-captcha/checkpoint-700/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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 %}

lora/sft-captcha/checkpoint-700/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddb527f07a922693764c931a34b0ea01f4366b3002d99e4c23e2b018833cf4c5
+size 528907898