Model save

README.md

@@ -1,199 +1,58 @@
 ---
+base_model: Qwen/Qwen2-VL-2B-Instruct
 library_name: transformers
-tags: []
+model_name: Qwen2-VL-2B-Instruct-SFT-Clevr_CoGenT_TrainA_R1
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
 ---
 
-# Model Card for Model ID
+# Model Card for Qwen2-VL-2B-Instruct-SFT-Clevr_CoGenT_TrainA_R1
 
-<!-- Provide a quick summary of what the model is/does. -->
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
+## Quick start
 
+```python
+from transformers import pipeline
 
-## Model Details
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="BleachNick/Qwen2-VL-2B-Instruct-SFT-Clevr_CoGenT_TrainA_R1", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-### Model Description
+## Training procedure
 
-<!-- Provide a longer summary of what this model is. -->
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/haozhezhao/huggingface/runs/9hjq1oia) 
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
 
-- **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]
+This model was trained with SFT.
 
-### Model Sources [optional]
+### Framework versions
 
-<!-- Provide the basic links for the model. -->
+- TRL: 0.14.0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+## Citations
 
-## 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]
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9991532599491956,
+    "total_flos": 8.380405739893555e+17,
+    "train_loss": 0.6345516301817813,
+    "train_runtime": 3216.2267,
+    "train_samples": 37773,
+    "train_samples_per_second": 11.745,
+    "train_steps_per_second": 0.092
+}

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "attn_implementation": null,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e261fdc4bc23a8089af0f9990a21e4e755e0bb4f9af7a8368db050d82e8d910
+size 4884798456

tokenizer_config.json

@@ -138,7 +138,6 @@
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
-  "processor_class": "Qwen2VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9991532599491956,
+    "total_flos": 8.380405739893555e+17,
+    "train_loss": 0.6345516301817813,
+    "train_runtime": 3216.2267,
+    "train_samples": 37773,
+    "train_samples_per_second": 11.745,
+    "train_steps_per_second": 0.092
+}

trainer_state.json

@@ -0,0 +1,455 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9991532599491956,
+  "eval_steps": 500,
+  "global_step": 295,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01693480101608806,
+      "grad_norm": 11.07681941986084,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.8357,
+      "step": 5
+    },
+    {
+      "epoch": 0.03386960203217612,
+      "grad_norm": 4.368485450744629,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.6208,
+      "step": 10
+    },
+    {
+      "epoch": 0.05080440304826418,
+      "grad_norm": 2.597416877746582,
+      "learning_rate": 1e-05,
+      "loss": 1.2437,
+      "step": 15
+    },
+    {
+      "epoch": 0.06773920406435224,
+      "grad_norm": 2.159755229949951,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.9804,
+      "step": 20
+    },
+    {
+      "epoch": 0.0846740050804403,
+      "grad_norm": 1.7200169563293457,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.8607,
+      "step": 25
+    },
+    {
+      "epoch": 0.10160880609652836,
+      "grad_norm": 1.2486546039581299,
+      "learning_rate": 2e-05,
+      "loss": 0.7869,
+      "step": 30
+    },
+    {
+      "epoch": 0.11854360711261643,
+      "grad_norm": 1.2447178363800049,
+      "learning_rate": 1.9982437317643218e-05,
+      "loss": 0.7324,
+      "step": 35
+    },
+    {
+      "epoch": 0.1354784081287045,
+      "grad_norm": 1.129758358001709,
+      "learning_rate": 1.992981096013517e-05,
+      "loss": 0.7058,
+      "step": 40
+    },
+    {
+      "epoch": 0.15241320914479256,
+      "grad_norm": 0.9256328344345093,
+      "learning_rate": 1.984230577947597e-05,
+      "loss": 0.6845,
+      "step": 45
+    },
+    {
+      "epoch": 0.1693480101608806,
+      "grad_norm": 0.9811558723449707,
+      "learning_rate": 1.972022914080411e-05,
+      "loss": 0.6698,
+      "step": 50
+    },
+    {
+      "epoch": 0.18628281117696868,
+      "grad_norm": 1.0069135427474976,
+      "learning_rate": 1.9564009842765225e-05,
+      "loss": 0.6393,
+      "step": 55
+    },
+    {
+      "epoch": 0.20321761219305673,
+      "grad_norm": 0.9143001437187195,
+      "learning_rate": 1.9374196611341212e-05,
+      "loss": 0.6321,
+      "step": 60
+    },
+    {
+      "epoch": 0.2201524132091448,
+      "grad_norm": 0.9945001006126404,
+      "learning_rate": 1.9151456172430186e-05,
+      "loss": 0.6286,
+      "step": 65
+    },
+    {
+      "epoch": 0.23708721422523285,
+      "grad_norm": 0.9755650758743286,
+      "learning_rate": 1.8896570909947477e-05,
+      "loss": 0.6178,
+      "step": 70
+    },
+    {
+      "epoch": 0.2540220152413209,
+      "grad_norm": 0.9144276976585388,
+      "learning_rate": 1.8610436117673557e-05,
+      "loss": 0.6204,
+      "step": 75
+    },
+    {
+      "epoch": 0.270956816257409,
+      "grad_norm": 0.9252317547798157,
+      "learning_rate": 1.829405685450202e-05,
+      "loss": 0.6124,
+      "step": 80
+    },
+    {
+      "epoch": 0.28789161727349705,
+      "grad_norm": 0.7833272218704224,
+      "learning_rate": 1.7948544414133534e-05,
+      "loss": 0.5958,
+      "step": 85
+    },
+    {
+      "epoch": 0.3048264182895851,
+      "grad_norm": 0.8833147883415222,
+      "learning_rate": 1.7575112421616203e-05,
+      "loss": 0.6049,
+      "step": 90
+    },
+    {
+      "epoch": 0.32176121930567314,
+      "grad_norm": 0.8253676295280457,
+      "learning_rate": 1.717507257044331e-05,
+      "loss": 0.5905,
+      "step": 95
+    },
+    {
+      "epoch": 0.3386960203217612,
+      "grad_norm": 0.800396740436554,
+      "learning_rate": 1.6749830015182106e-05,
+      "loss": 0.5698,
+      "step": 100
+    },
+    {
+      "epoch": 0.3556308213378493,
+      "grad_norm": 0.9177567362785339,
+      "learning_rate": 1.6300878435817115e-05,
+      "loss": 0.5787,
+      "step": 105
+    },
+    {
+      "epoch": 0.37256562235393736,
+      "grad_norm": 0.8931817412376404,
+      "learning_rate": 1.5829794791144723e-05,
+      "loss": 0.5748,
+      "step": 110
+    },
+    {
+      "epoch": 0.3895004233700254,
+      "grad_norm": 1.0776097774505615,
+      "learning_rate": 1.533823377964791e-05,
+      "loss": 0.5693,
+      "step": 115
+    },
+    {
+      "epoch": 0.40643522438611346,
+      "grad_norm": 0.9571148157119751,
+      "learning_rate": 1.482792202730745e-05,
+      "loss": 0.5795,
+      "step": 120
+    },
+    {
+      "epoch": 0.42337002540220153,
+      "grad_norm": 0.9276224970817566,
+      "learning_rate": 1.4300652022765207e-05,
+      "loss": 0.5744,
+      "step": 125
+    },
+    {
+      "epoch": 0.4403048264182896,
+      "grad_norm": 0.8562670350074768,
+      "learning_rate": 1.3758275821142382e-05,
+      "loss": 0.574,
+      "step": 130
+    },
+    {
+      "epoch": 0.4572396274343776,
+      "grad_norm": 0.987328827381134,
+      "learning_rate": 1.3202698538628376e-05,
+      "loss": 0.5612,
+      "step": 135
+    },
+    {
+      "epoch": 0.4741744284504657,
+      "grad_norm": 0.7609542012214661,
+      "learning_rate": 1.2635871660690677e-05,
+      "loss": 0.5608,
+      "step": 140
+    },
+    {
+      "epoch": 0.4911092294665538,
+      "grad_norm": 0.752984881401062,
+      "learning_rate": 1.2059786187410984e-05,
+      "loss": 0.5462,
+      "step": 145
+    },
+    {
+      "epoch": 0.5080440304826418,
+      "grad_norm": 0.7577420473098755,
+      "learning_rate": 1.1476465640024814e-05,
+      "loss": 0.5565,
+      "step": 150
+    },
+    {
+      "epoch": 0.5249788314987299,
+      "grad_norm": 0.7515721321105957,
+      "learning_rate": 1.0887958953229349e-05,
+      "loss": 0.5475,
+      "step": 155
+    },
+    {
+      "epoch": 0.541913632514818,
+      "grad_norm": 0.7427639961242676,
+      "learning_rate": 1.0296333278225599e-05,
+      "loss": 0.5561,
+      "step": 160
+    },
+    {
+      "epoch": 0.558848433530906,
+      "grad_norm": 0.8810573816299438,
+      "learning_rate": 9.703666721774403e-06,
+      "loss": 0.5391,
+      "step": 165
+    },
+    {
+      "epoch": 0.5757832345469941,
+      "grad_norm": 0.7623007297515869,
+      "learning_rate": 9.112041046770653e-06,
+      "loss": 0.5504,
+      "step": 170
+    },
+    {
+      "epoch": 0.5927180355630821,
+      "grad_norm": 0.7749871015548706,
+      "learning_rate": 8.52353435997519e-06,
+      "loss": 0.5442,
+      "step": 175
+    },
+    {
+      "epoch": 0.6096528365791702,
+      "grad_norm": 0.731037974357605,
+      "learning_rate": 7.940213812589018e-06,
+      "loss": 0.5504,
+      "step": 180
+    },
+    {
+      "epoch": 0.6265876375952583,
+      "grad_norm": 0.6718469262123108,
+      "learning_rate": 7.364128339309326e-06,
+      "loss": 0.5461,
+      "step": 185
+    },
+    {
+      "epoch": 0.6435224386113463,
+      "grad_norm": 0.7169979214668274,
+      "learning_rate": 6.797301461371626e-06,
+      "loss": 0.5387,
+      "step": 190
+    },
+    {
+      "epoch": 0.6604572396274344,
+      "grad_norm": 0.6952066421508789,
+      "learning_rate": 6.241724178857621e-06,
+      "loss": 0.5391,
+      "step": 195
+    },
+    {
+      "epoch": 0.6773920406435224,
+      "grad_norm": 0.7324413657188416,
+      "learning_rate": 5.699347977234799e-06,
+      "loss": 0.5351,
+      "step": 200
+    },
+    {
+      "epoch": 0.6943268416596104,
+      "grad_norm": 0.7053231596946716,
+      "learning_rate": 5.172077972692553e-06,
+      "loss": 0.5393,
+      "step": 205
+    },
+    {
+      "epoch": 0.7112616426756986,
+      "grad_norm": 0.6486250758171082,
+      "learning_rate": 4.661766220352098e-06,
+      "loss": 0.5311,
+      "step": 210
+    },
+    {
+      "epoch": 0.7281964436917866,
+      "grad_norm": 0.6176902055740356,
+      "learning_rate": 4.170205208855281e-06,
+      "loss": 0.5342,
+      "step": 215
+    },
+    {
+      "epoch": 0.7451312447078747,
+      "grad_norm": 0.6902855634689331,
+      "learning_rate": 3.6991215641828903e-06,
+      "loss": 0.526,
+      "step": 220
+    },
+    {
+      "epoch": 0.7620660457239627,
+      "grad_norm": 0.6924082636833191,
+      "learning_rate": 3.250169984817897e-06,
+      "loss": 0.5393,
+      "step": 225
+    },
+    {
+      "epoch": 0.7790008467400508,
+      "grad_norm": 0.6927950978279114,
+      "learning_rate": 2.8249274295566863e-06,
+      "loss": 0.5372,
+      "step": 230
+    },
+    {
+      "epoch": 0.7959356477561389,
+      "grad_norm": 0.6544324159622192,
+      "learning_rate": 2.424887578383799e-06,
+      "loss": 0.53,
+      "step": 235
+    },
+    {
+      "epoch": 0.8128704487722269,
+      "grad_norm": 0.6218433976173401,
+      "learning_rate": 2.0514555858664663e-06,
+      "loss": 0.5383,
+      "step": 240
+    },
+    {
+      "epoch": 0.8298052497883149,
+      "grad_norm": 0.6293333172798157,
+      "learning_rate": 1.7059431454979825e-06,
+      "loss": 0.5242,
+      "step": 245
+    },
+    {
+      "epoch": 0.8467400508044031,
+      "grad_norm": 0.6629937291145325,
+      "learning_rate": 1.3895638823264447e-06,
+      "loss": 0.5283,
+      "step": 250
+    },
+    {
+      "epoch": 0.8636748518204911,
+      "grad_norm": 0.6638931632041931,
+      "learning_rate": 1.1034290900525279e-06,
+      "loss": 0.5346,
+      "step": 255
+    },
+    {
+      "epoch": 0.8806096528365792,
+      "grad_norm": 0.6154753565788269,
+      "learning_rate": 8.485438275698154e-07,
+      "loss": 0.5286,
+      "step": 260
+    },
+    {
+      "epoch": 0.8975444538526672,
+      "grad_norm": 0.5576867461204529,
+      "learning_rate": 6.258033886587911e-07,
+      "loss": 0.5197,
+      "step": 265
+    },
+    {
+      "epoch": 0.9144792548687553,
+      "grad_norm": 0.5925081372261047,
+      "learning_rate": 4.359901572347758e-07,
+      "loss": 0.5272,
+      "step": 270
+    },
+    {
+      "epoch": 0.9314140558848434,
+      "grad_norm": 0.8894816040992737,
+      "learning_rate": 2.7977085919589253e-07,
+      "loss": 0.5229,
+      "step": 275
+    },
+    {
+      "epoch": 0.9483488569009314,
+      "grad_norm": 0.613675057888031,
+      "learning_rate": 1.5769422052403172e-07,
+      "loss": 0.5336,
+      "step": 280
+    },
+    {
+      "epoch": 0.9652836579170194,
+      "grad_norm": 0.5702030658721924,
+      "learning_rate": 7.018903986483083e-08,
+      "loss": 0.5295,
+      "step": 285
+    },
+    {
+      "epoch": 0.9822184589331076,
+      "grad_norm": 0.6007622480392456,
+      "learning_rate": 1.7562682356786488e-08,
+      "loss": 0.5357,
+      "step": 290
+    },
+    {
+      "epoch": 0.9991532599491956,
+      "grad_norm": 0.5643032193183899,
+      "learning_rate": 0.0,
+      "loss": 0.5246,
+      "step": 295
+    },
+    {
+      "epoch": 0.9991532599491956,
+      "step": 295,
+      "total_flos": 8.380405739893555e+17,
+      "train_loss": 0.6345516301817813,
+      "train_runtime": 3216.2267,
+      "train_samples_per_second": 11.745,
+      "train_steps_per_second": 0.092
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 295,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.380405739893555e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3810921b32631cca3754c3b8840ae85e3f3f5d65d48e95c60d784ac85c960652
+size 7224