Upload 8 files

README.md

@@ -1,3 +1,218 @@
 ---
-license: apache-2.0
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
 ---
+
+# 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]
+
+
+## Training procedure
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+- PEFT 0.6.3.dev0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "lm_head",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59bc1cc013d8c788d37cdb06720fb4dd06aaed94360dca2f59f86a96e8729c5
+size 864513616

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afb7bf3b2d006016605a57a695f47c487c7b6dcf45665cd1cc7d6bc7cd4890af
+size 170951516

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e857436592ff676174e03d082869ffdfe96431bfc401555e8c6adc65dc1158d9
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4d6d865d6518a82dd54bb09f8f02628ebe31ca8be097a65ef5c8faff7622969
+size 1064

trainer_state.json

@@ -0,0 +1,580 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "eval_steps": 25,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.43993993993994e-05,
+      "loss": 0.8345,
+      "step": 25
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.1825820505619049,
+      "eval_runtime": 19.7988,
+      "eval_samples_per_second": 5.051,
+      "eval_steps_per_second": 0.657,
+      "step": 25
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.3773773773773775e-05,
+      "loss": 0.1821,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.130362868309021,
+      "eval_runtime": 19.6459,
+      "eval_samples_per_second": 5.09,
+      "eval_steps_per_second": 0.662,
+      "step": 50
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.314814814814815e-05,
+      "loss": 0.1276,
+      "step": 75
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.11436057090759277,
+      "eval_runtime": 19.6323,
+      "eval_samples_per_second": 5.094,
+      "eval_steps_per_second": 0.662,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.2522522522522523e-05,
+      "loss": 0.127,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.09521650522947311,
+      "eval_runtime": 20.0255,
+      "eval_samples_per_second": 4.994,
+      "eval_steps_per_second": 0.649,
+      "step": 100
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.18968968968969e-05,
+      "loss": 0.1018,
+      "step": 125
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.08395165205001831,
+      "eval_runtime": 19.6593,
+      "eval_samples_per_second": 5.087,
+      "eval_steps_per_second": 0.661,
+      "step": 125
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.1271271271271275e-05,
+      "loss": 0.0971,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.08126174658536911,
+      "eval_runtime": 19.9094,
+      "eval_samples_per_second": 5.023,
+      "eval_steps_per_second": 0.653,
+      "step": 150
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.0645645645645647e-05,
+      "loss": 0.0837,
+      "step": 175
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 0.06755229830741882,
+      "eval_runtime": 19.8387,
+      "eval_samples_per_second": 5.041,
+      "eval_steps_per_second": 0.655,
+      "step": 175
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.0020020020020023e-05,
+      "loss": 0.0779,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.06234545633196831,
+      "eval_runtime": 20.1113,
+      "eval_samples_per_second": 4.972,
+      "eval_steps_per_second": 0.646,
+      "step": 200
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 1.9394394394394395e-05,
+      "loss": 0.0638,
+      "step": 225
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 0.059754613786935806,
+      "eval_runtime": 20.0532,
+      "eval_samples_per_second": 4.987,
+      "eval_steps_per_second": 0.648,
+      "step": 225
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 1.8768768768768768e-05,
+      "loss": 0.0713,
+      "step": 250
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.05015714094042778,
+      "eval_runtime": 19.9208,
+      "eval_samples_per_second": 5.02,
+      "eval_steps_per_second": 0.653,
+      "step": 250
+    },
+    {
+      "epoch": 5.5,
+      "learning_rate": 1.8143143143143144e-05,
+      "loss": 0.0507,
+      "step": 275
+    },
+    {
+      "epoch": 5.5,
+      "eval_loss": 0.04916694015264511,
+      "eval_runtime": 20.02,
+      "eval_samples_per_second": 4.995,
+      "eval_steps_per_second": 0.649,
+      "step": 275
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.7517517517517516e-05,
+      "loss": 0.0613,
+      "step": 300
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.04311186820268631,
+      "eval_runtime": 19.861,
+      "eval_samples_per_second": 5.035,
+      "eval_steps_per_second": 0.655,
+      "step": 300
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 1.6891891891891892e-05,
+      "loss": 0.046,
+      "step": 325
+    },
+    {
+      "epoch": 6.5,
+      "eval_loss": 0.04042712226510048,
+      "eval_runtime": 20.213,
+      "eval_samples_per_second": 4.947,
+      "eval_steps_per_second": 0.643,
+      "step": 325
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.6266266266266268e-05,
+      "loss": 0.0487,
+      "step": 350
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.036048341542482376,
+      "eval_runtime": 19.868,
+      "eval_samples_per_second": 5.033,
+      "eval_steps_per_second": 0.654,
+      "step": 350
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 1.564064064064064e-05,
+      "loss": 0.0402,
+      "step": 375
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 0.03601359948515892,
+      "eval_runtime": 19.7933,
+      "eval_samples_per_second": 5.052,
+      "eval_steps_per_second": 0.657,
+      "step": 375
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.5015015015015016e-05,
+      "loss": 0.0433,
+      "step": 400
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.03563099354505539,
+      "eval_runtime": 19.939,
+      "eval_samples_per_second": 5.015,
+      "eval_steps_per_second": 0.652,
+      "step": 400
+    },
+    {
+      "epoch": 8.5,
+      "learning_rate": 1.438938938938939e-05,
+      "loss": 0.0356,
+      "step": 425
+    },
+    {
+      "epoch": 8.5,
+      "eval_loss": 0.03060692362487316,
+      "eval_runtime": 20.0337,
+      "eval_samples_per_second": 4.992,
+      "eval_steps_per_second": 0.649,
+      "step": 425
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.3763763763763765e-05,
+      "loss": 0.0378,
+      "step": 450
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.03127852827310562,
+      "eval_runtime": 19.9074,
+      "eval_samples_per_second": 5.023,
+      "eval_steps_per_second": 0.653,
+      "step": 450
+    },
+    {
+      "epoch": 9.5,
+      "learning_rate": 1.3138138138138139e-05,
+      "loss": 0.0332,
+      "step": 475
+    },
+    {
+      "epoch": 9.5,
+      "eval_loss": 0.029647212475538254,
+      "eval_runtime": 19.6987,
+      "eval_samples_per_second": 5.076,
+      "eval_steps_per_second": 0.66,
+      "step": 475
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.2512512512512515e-05,
+      "loss": 0.0346,
+      "step": 500
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.028394926339387894,
+      "eval_runtime": 19.9244,
+      "eval_samples_per_second": 5.019,
+      "eval_steps_per_second": 0.652,
+      "step": 500
+    },
+    {
+      "epoch": 10.5,
+      "learning_rate": 1.1886886886886887e-05,
+      "loss": 0.0303,
+      "step": 525
+    },
+    {
+      "epoch": 10.5,
+      "eval_loss": 0.02781710773706436,
+      "eval_runtime": 19.8483,
+      "eval_samples_per_second": 5.038,
+      "eval_steps_per_second": 0.655,
+      "step": 525
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 1.1261261261261261e-05,
+      "loss": 0.0322,
+      "step": 550
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.02787485532462597,
+      "eval_runtime": 20.0578,
+      "eval_samples_per_second": 4.986,
+      "eval_steps_per_second": 0.648,
+      "step": 550
+    },
+    {
+      "epoch": 11.5,
+      "learning_rate": 1.0635635635635637e-05,
+      "loss": 0.0311,
+      "step": 575
+    },
+    {
+      "epoch": 11.5,
+      "eval_loss": 0.026974568143486977,
+      "eval_runtime": 20.0373,
+      "eval_samples_per_second": 4.991,
+      "eval_steps_per_second": 0.649,
+      "step": 575
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 1.0010010010010011e-05,
+      "loss": 0.0295,
+      "step": 600
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.02675173431634903,
+      "eval_runtime": 20.0507,
+      "eval_samples_per_second": 4.987,
+      "eval_steps_per_second": 0.648,
+      "step": 600
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 9.384384384384384e-06,
+      "loss": 0.0276,
+      "step": 625
+    },
+    {
+      "epoch": 12.5,
+      "eval_loss": 0.026049189269542694,
+      "eval_runtime": 19.7691,
+      "eval_samples_per_second": 5.058,
+      "eval_steps_per_second": 0.658,
+      "step": 625
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 8.758758758758758e-06,
+      "loss": 0.0303,
+      "step": 650
+    },
+    {
+      "epoch": 13.0,
+      "eval_loss": 0.025803018361330032,
+      "eval_runtime": 20.0235,
+      "eval_samples_per_second": 4.994,
+      "eval_steps_per_second": 0.649,
+      "step": 650
+    },
+    {
+      "epoch": 13.5,
+      "learning_rate": 8.133133133133134e-06,
+      "loss": 0.0258,
+      "step": 675
+    },
+    {
+      "epoch": 13.5,
+      "eval_loss": 0.024792619049549103,
+      "eval_runtime": 20.0588,
+      "eval_samples_per_second": 4.985,
+      "eval_steps_per_second": 0.648,
+      "step": 675
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 7.507507507507508e-06,
+      "loss": 0.0277,
+      "step": 700
+    },
+    {
+      "epoch": 14.0,
+      "eval_loss": 0.024141492322087288,
+      "eval_runtime": 20.0508,
+      "eval_samples_per_second": 4.987,
+      "eval_steps_per_second": 0.648,
+      "step": 700
+    },
+    {
+      "epoch": 14.5,
+      "learning_rate": 6.881881881881882e-06,
+      "loss": 0.0253,
+      "step": 725
+    },
+    {
+      "epoch": 14.5,
+      "eval_loss": 0.024363957345485687,
+      "eval_runtime": 20.0138,
+      "eval_samples_per_second": 4.997,
+      "eval_steps_per_second": 0.65,
+      "step": 725
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 6.256256256256257e-06,
+      "loss": 0.0272,
+      "step": 750
+    },
+    {
+      "epoch": 15.0,
+      "eval_loss": 0.02408401481807232,
+      "eval_runtime": 20.0671,
+      "eval_samples_per_second": 4.983,
+      "eval_steps_per_second": 0.648,
+      "step": 750
+    },
+    {
+      "epoch": 15.5,
+      "learning_rate": 5.630630630630631e-06,
+      "loss": 0.0244,
+      "step": 775
+    },
+    {
+      "epoch": 15.5,
+      "eval_loss": 0.024250097572803497,
+      "eval_runtime": 20.0673,
+      "eval_samples_per_second": 4.983,
+      "eval_steps_per_second": 0.648,
+      "step": 775
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 5.005005005005006e-06,
+      "loss": 0.027,
+      "step": 800
+    },
+    {
+      "epoch": 16.0,
+      "eval_loss": 0.02365710586309433,
+      "eval_runtime": 19.9778,
+      "eval_samples_per_second": 5.006,
+      "eval_steps_per_second": 0.651,
+      "step": 800
+    },
+    {
+      "epoch": 16.5,
+      "learning_rate": 4.379379379379379e-06,
+      "loss": 0.0243,
+      "step": 825
+    },
+    {
+      "epoch": 16.5,
+      "eval_loss": 0.023755939677357674,
+      "eval_runtime": 20.1906,
+      "eval_samples_per_second": 4.953,
+      "eval_steps_per_second": 0.644,
+      "step": 825
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 3.753753753753754e-06,
+      "loss": 0.0255,
+      "step": 850
+    },
+    {
+      "epoch": 17.0,
+      "eval_loss": 0.02352030761539936,
+      "eval_runtime": 19.829,
+      "eval_samples_per_second": 5.043,
+      "eval_steps_per_second": 0.656,
+      "step": 850
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 3.1281281281281287e-06,
+      "loss": 0.0242,
+      "step": 875
+    },
+    {
+      "epoch": 17.5,
+      "eval_loss": 0.023568786680698395,
+      "eval_runtime": 19.7648,
+      "eval_samples_per_second": 5.059,
+      "eval_steps_per_second": 0.658,
+      "step": 875
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 2.502502502502503e-06,
+      "loss": 0.0248,
+      "step": 900
+    },
+    {
+      "epoch": 18.0,
+      "eval_loss": 0.02345026656985283,
+      "eval_runtime": 20.0421,
+      "eval_samples_per_second": 4.99,
+      "eval_steps_per_second": 0.649,
+      "step": 900
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 1.876876876876877e-06,
+      "loss": 0.0237,
+      "step": 925
+    },
+    {
+      "epoch": 18.5,
+      "eval_loss": 0.023420894518494606,
+      "eval_runtime": 19.882,
+      "eval_samples_per_second": 5.03,
+      "eval_steps_per_second": 0.654,
+      "step": 925
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 1.2512512512512514e-06,
+      "loss": 0.0244,
+      "step": 950
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 0.023358002305030823,
+      "eval_runtime": 19.6722,
+      "eval_samples_per_second": 5.083,
+      "eval_steps_per_second": 0.661,
+      "step": 950
+    },
+    {
+      "epoch": 19.5,
+      "learning_rate": 6.256256256256257e-07,
+      "loss": 0.0233,
+      "step": 975
+    },
+    {
+      "epoch": 19.5,
+      "eval_loss": 0.02332903817296028,
+      "eval_runtime": 19.7534,
+      "eval_samples_per_second": 5.062,
+      "eval_steps_per_second": 0.658,
+      "step": 975
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 0.0,
+      "loss": 0.0238,
+      "step": 1000
+    },
+    {
+      "epoch": 20.0,
+      "eval_loss": 0.023337021470069885,
+      "eval_runtime": 20.0001,
+      "eval_samples_per_second": 5.0,
+      "eval_steps_per_second": 0.65,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 25,
+  "total_flos": 4.4210388467712e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:061cf51e5d7fd9b973f00eb4986e6b5c3d4e707ab6b94679781316b11fdab1f9
+size 4728