AwAppp
/

benchmark_original_batch_size30

Transformers

Model card Files Files and versions

xet

Community

AwAppp commited on Mar 6, 2024

Commit

bd8d7d9

verified ·

1 Parent(s): 0a4d41a

Upload TextGenerationReport

Browse files

Files changed (2) hide show

README.md +199 -0
benchmark_report.json +608 -0

README.md ADDED Viewed

	@@ -0,0 +1,199 @@

+---
+library_name: transformers
+tags: []
+---
+# 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. -->
+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]
+### 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]

benchmark_report.json ADDED Viewed

	@@ -0,0 +1,608 @@

+{
+    "prefill": {
+        "memory": {
+            "unit": "MB",
+            "max_ram": 1476.370432,
+            "max_vram": 15674.114048,
+            "max_reserved": 15189.671936,
+            "max_allocated": 15039.57248
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 0.04065064185227804,
+            "stdev": 0.00010230905193306444,
+            "values": [
+                0.041487518310546874,
+                0.04111769485473633,
+                0.04118214416503906,
+                0.041109504699707033,
+                0.04109619140625,
+                0.041133056640625,
+                0.04107571029663086,
+                0.0411514892578125,
+                0.04080640029907227,
+                0.04065689468383789,
+                0.040659969329833984,
+                0.04064665603637695,
+                0.040667198181152345,
+                0.04075212860107422,
+                0.04067839813232422,
+                0.04067225646972656,
+                0.04067737579345703,
+                0.040643585205078124,
+                0.04069171142578125,
+                0.04068454360961914,
+                0.04066611099243164,
+                0.04066918563842774,
+                0.04065689468383789,
+                0.0406558723449707,
+                0.04067843246459961,
+                0.04065484619140625,
+                0.04063129425048828,
+                0.04063948822021484,
+                0.04067020797729492,
+                0.040681472778320314,
+                0.040630271911621094,
+                0.04066611099243164,
+                0.04063129425048828,
+                0.04068454360961914,
+                0.04065280151367188,
+                0.0406743049621582,
+                0.040622081756591794,
+                0.04061695861816406,
+                0.04065792083740234,
+                0.04067020797729492,
+                0.04065785598754883,
+                0.04067532730102539,
+                0.04062412643432617,
+                0.040668159484863284,
+                0.04062412643432617,
+                0.040653759002685544,
+                0.04060671997070313,
+                0.04059852981567383,
+                0.04067331314086914,
+                0.04066304016113281,
+                0.040662017822265625,
+                0.04062003326416016,
+                0.04063641738891602,
+                0.04062617492675781,
+                0.040627201080322264,
+                0.040610816955566405,
+                0.040651775360107424,
+                0.040619007110595705,
+                0.04065075302124024,
+                0.040591358184814456,
+                0.04067225646972656,
+                0.040651775360107424,
+                0.04060361480712891,
+                0.04058726501464844,
+                0.040630271911621094,
+                0.0406743049621582,
+                0.04060467147827149,
+                0.040671230316162106,
+                0.040635391235351564,
+                0.040648704528808595,
+                0.04063641738891602,
+                0.04063334274291992,
+                0.04064255905151367,
+                0.04060876846313476,
+                0.04062617492675781,
+                0.040627201080322264,
+                0.04061798477172852,
+                0.040632320404052735,
+                0.04068966293334961,
+                0.04062515258789062,
+                0.040619007110595705,
+                0.040643585205078124,
+                0.04064460754394531,
+                0.04069068908691406,
+                0.04065075302124024,
+                0.04064051055908203,
+                0.04063846588134765,
+                0.04064761734008789,
+                0.04061183929443359,
+                0.040648704528808595,
+                0.040653823852539066,
+                0.040615936279296876,
+                0.040612865447998046,
+                0.04060160064697266,
+                0.040612865447998046,
+                0.04061695861816406,
+                0.04062617492675781,
+                0.040626144409179686,
+                0.04059852981567383,
+                0.04064153671264648,
+                0.040645633697509766,
+                0.04066099166870117,
+                0.04064255905151367,
+                0.040627201080322264,
+                0.040645633697509766,
+                0.0406558723449707,
+                0.040627201080322264,
+                0.04060671997070313,
+                0.04060876846313476,
+                0.04066611099243164,
+                0.04062515258789062,
+                0.040668159484863284,
+                0.040599552154541016,
+                0.040635391235351564,
+                0.0405852165222168,
+                0.04064255905151367,
+                0.0406363525390625,
+                0.040629249572753906,
+                0.04060569763183594,
+                0.040639457702636717,
+                0.040591358184814456,
+                0.04069683074951172,
+                0.04065484619140625,
+                0.040630271911621094,
+                0.040621055603027346,
+                0.04062412643432617,
+                0.040635391235351564,
+                0.04063126373291016,
+                0.04069683074951172,
+                0.04060467147827149,
+                0.040632320404052735,
+                0.040591358184814456,
+                0.04063846588134765,
+                0.040629249572753906,
+                0.04057395172119141,
+                0.040615936279296876,
+                0.04061491012573242,
+                0.04060979080200195,
+                0.04063436889648438,
+                0.04067225646972656,
+                0.040615936279296876,
+                0.040594432830810545,
+                0.04062310409545898,
+                0.04065689468383789,
+                0.04064153671264648,
+                0.04060979080200195,
+                0.04064153671264648,
+                0.040667137145996096,
+                0.04063948822021484,
+                0.04063536071777344,
+                0.04062822341918945,
+                0.040630271911621094,
+                0.040621055603027346,
+                0.04060876846313476,
+                0.04065484619140625,
+                0.040635391235351564,
+                0.04059545516967773,
+                0.04063641738891602,
+                0.040668159484863284,
+                0.04061491012573242,
+                0.04062412643432617,
+                0.04060671997070313,
+                0.04063641738891602,
+                0.040643585205078124,
+                0.04061183929443359,
+                0.04064153671264648,
+                0.04061183929443359,
+                0.04061695861816406,
+                0.04060774230957031,
+                0.04069887924194336,
+                0.04062822341918945,
+                0.040651775360107424,
+                0.04064255905151367,
+                0.04060160064697266,
+                0.04059033584594727,
+                0.040597503662109374,
+                0.04060671997070313,
+                0.04063948822021484,
+                0.04062508773803711,
+                0.040602622985839845,
+                0.040600574493408204,
+                0.04062515258789062,
+                0.04063334274291992,
+                0.040602622985839845,
+                0.040643585205078124,
+                0.0406036491394043,
+                0.040553470611572266,
+                0.04062515258789062,
+                0.0405852165222168,
+                0.04061695861816406,
+                0.04059648132324219,
+                0.040636318206787106,
+                0.04065894317626953,
+                0.040592384338378903,
+                0.040594432830810545,
+                0.040567806243896484,
+                0.040629249572753906,
+                0.040667137145996096,
+                0.04060876846313476,
+                0.0406640625,
+                0.04064255905151367,
+                0.04064665603637695,
+                0.04066099166870117,
+                0.04061798477172852,
+                0.04067225646972656,
+                0.04062412643432617,
+                0.04062822341918945,
+                0.04063334274291992,
+                0.04062617492675781,
+                0.04062003326416016,
+                0.04063334274291992,
+                0.04061491012573242,
+                0.040612831115722656,
+                0.04061695861816406,
+                0.040630271911621094,
+                0.04062819290161133,
+                0.04060467147827149,
+                0.040615936279296876,
+                0.040584190368652344,
+                0.04062822341918945,
+                0.040584190368652344,
+                0.04065075302124024,
+                0.04058828735351563,
+                0.04060979080200195,
+                0.040586238861083986,
+                0.040658912658691405,
+                0.040615936279296876,
+                0.040602657318115236,
+                0.040597503662109374,
+                0.04064460754394531,
+                0.04060569763183594,
+                0.040645633697509766,
+                0.040668159484863284,
+                0.04064051055908203,
+                0.040639457702636717,
+                0.04060671997070313,
+                0.040621055603027346,
+                0.04062617492675781,
+                0.04065894317626953,
+                0.04061798477172852,
+                0.040553470611572266,
+                0.04061798477172852,
+                0.04057395172119141,
+                0.04067327880859375,
+                0.04055244827270508,
+                0.040610816955566405
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 787.1954424799995
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "decode": {
+        "memory": {
+            "unit": "MB",
+            "max_ram": 1487.609856,
+            "max_vram": 15739.12576,
+            "max_reserved": 15254.683648,
+            "max_allocated": 15101.761024
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 3.71031038792928,
+            "stdev": 0.0003956553636294078,
+            "values": [
+                3.710101493835448,
+                3.709965293884277,
+                3.7108643760681166
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.3648076031999
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "per_token": {
+        "memory": null,
+        "latency": {
+            "unit": "s",
+            "mean": 0.03747788270635637,
+            "stdev": 0.00015737209717694308,
+            "values": [
+                0.03731660842895508,
+                0.03723263931274414,
+                0.03724390411376953,
+                0.037253120422363284,
+                0.037149696350097655,
+                0.03721113586425781,
+                0.0373043212890625,
+                0.03723263931274414,
+                0.037223423004150394,
+                0.037269504547119144,
+                0.037275646209716795,
+                0.037269504547119144,
+                0.03726233673095703,
+                0.03732275390625,
+                0.03732070541381836,
+                0.037282817840576174,
+                0.03727667236328125,
+                0.03727155303955078,
+                0.03728902435302734,
+                0.03730425643920898,
+                0.03723980712890625,
+                0.03729612731933594,
+                0.03729919815063477,
+                0.03730124664306641,
+                0.03727155303955078,
+                0.037379070281982424,
+                0.03734527969360352,
+                0.03736576080322265,
+                0.037348350524902346,
+                0.03734220886230469,
+                0.037372928619384765,
+                0.03741183853149414,
+                0.037321727752685545,
+                0.037384193420410154,
+                0.037410816192626956,
+                0.037397502899169925,
+                0.037362686157226564,
+                0.03742617416381836,
+                0.03737497711181641,
+                0.03750809478759766,
+                0.03741798400878906,
+                0.03747123336791992,
+                0.037408767700195314,
+                0.0374917106628418,
+                0.037443584442138675,
+                0.03750713729858399,
+                0.03744147109985352,
+                0.037525505065917966,
+                0.03748147201538086,
+                0.037602302551269534,
+                0.03745177459716797,
+                0.037599231719970705,
+                0.03750297546386719,
+                0.037663745880126956,
+                0.037479423522949216,
+                0.03762179183959961,
+                0.03751625442504883,
+                0.0376545295715332,
+                0.03753881454467774,
+                0.03757670211791992,
+                0.037510143280029294,
+                0.03769753646850586,
+                0.03749273681640625,
+                0.03762073516845703,
+                0.037495807647705076,
+                0.03763507080078125,
+                0.03754905700683594,
+                0.03765657424926758,
+                0.03758489608764649,
+                0.03771084976196289,
+                0.0375470085144043,
+                0.03766067123413086,
+                0.037569534301757815,
+                0.03761971282958984,
+                0.03754393768310547,
+                0.037579776763916016,
+                0.03757363128662109,
+                0.03762483215332031,
+                0.03759001541137695,
+                0.03767091369628906,
+                0.037596160888671876,
+                0.037634048461914066,
+                0.037596160888671876,
+                0.03763302230834961,
+                0.03758899307250976,
+                0.037645313262939455,
+                0.03760947036743164,
+                0.03775078582763672,
+                0.03762278366088867,
+                0.0376627197265625,
+                0.037618686676025394,
+                0.03767196655273437,
+                0.03762377548217773,
+                0.03769651031494141,
+                0.03762483215332031,
+                0.03775283050537109,
+                0.03765350341796875,
+                0.03767910385131836,
+                0.03763916778564453,
+                0.03725823974609375,
+                0.037168128967285156,
+                0.0372305908203125,
+                0.03722137451171875,
+                0.03721625518798828,
+                0.03720601654052735,
+                0.0372408332824707,
+                0.03724185562133789,
+                0.037236736297607424,
+                0.03725823974609375,
+                0.03728384017944336,
+                0.03725721740722656,
+                0.03726233673095703,
+                0.03728486251831055,
+                0.03727974319458008,
+                0.0372674560546875,
+                0.037275646209716795,
+                0.03729305648803711,
+                0.0372592658996582,
+                0.037321727752685545,
+                0.03727052688598633,
+                0.037338111877441404,
+                0.037314590454101564,
+                0.03730326461791992,
+                0.03729817581176758,
+                0.037340160369873046,
+                0.03733196640014649,
+                0.037372928619384765,
+                0.037362686157226564,
+                0.037395454406738284,
+                0.037362686157226564,
+                0.03740671920776367,
+                0.037338111877441404,
+                0.03735859298706055,
+                0.03739852905273437,
+                0.037400577545166014,
+                0.037392383575439454,
+                0.03743334579467773,
+                0.037381118774414065,
+                0.03748761749267578,
+                0.03741593551635742,
+                0.037466110229492186,
+                0.03742924880981445,
+                0.03748761749267578,
+                0.03739648056030274,
+                0.03751321411132812,
+                0.03743231964111328,
+                0.037515262603759765,
+                0.0374835205078125,
+                0.03759107208251953,
+                0.037459934234619144,
+                0.03760025787353516,
+                0.03748556900024414,
+                0.037618686676025394,
+                0.03748863983154297,
+                0.03755212783813477,
+                0.03748147201538086,
+                0.037651454925537106,
+                0.03752755355834961,
+                0.03760435104370117,
+                0.03749587249755859,
+                0.03765958404541016,
+                0.037498878479003905,
+                0.03761151885986328,
+                0.03751321411132812,
+                0.03765964889526367,
+                0.037550079345703126,
+                0.0376545295715332,
+                0.0375470085144043,
+                0.037693504333496095,
+                0.03755923080444336,
+                0.03765248107910156,
+                0.037561344146728515,
+                0.03758796691894531,
+                0.037553150177001955,
+                0.03760844802856445,
+                0.037564414978027344,
+                0.037585918426513674,
+                0.03757875061035156,
+                0.0376995849609375,
+                0.037694465637207034,
+                0.03766988754272461,
+                0.03759820938110352,
+                0.03765862274169922,
+                0.03761670303344727,
+                0.037693374633789065,
+                0.03764940643310547,
+                0.037735424041748046,
+                0.03761459350585938,
+                0.0376360969543457,
+                0.037612545013427735,
+                0.03768627166748047,
+                0.037618686676025394,
+                0.03770163345336914,
+                0.03768832015991211,
+                0.037743614196777346,
+                0.037617664337158206,
+                0.037700607299804685,
+                0.03764223861694336,
+                0.03721932983398438,
+                0.03719782257080078,
+                0.037195777893066405,
+                0.03725107192993164,
+                0.03718348693847656,
+                0.03720806503295898,
+                0.03720601654052735,
+                0.0372674560546875,
+                0.03726540756225586,
+                0.03726847839355469,
+                0.0373043212890625,
+                0.03725721740722656,
+                0.03725823974609375,
+                0.037302272796630856,
+                0.037272575378417966,
+                0.03726335906982422,
+                0.03729919815063477,
+                0.037308414459228514,
+                0.03727667236328125,
+                0.03732275390625,
+                0.037321727752685545,
+                0.037308414459228514,
+                0.03731558227539063,
+                0.0373196792602539,
+                0.03730124664306641,
+                0.03737702560424805,
+                0.037338111877441404,
+                0.037343231201171875,
+                0.03738009643554688,
+                0.037369857788085936,
+                0.037386302947998044,
+                0.037415870666503905,
+                0.03736883163452148,
+                0.037392383575439454,
+                0.03740262222290039,
+                0.03740979385375977,
+                0.037392383575439454,
+                0.037440513610839846,
+                0.03739648056030274,
+                0.03745792007446289,
+                0.037438465118408204,
+                0.03747225570678711,
+                0.037425151824951174,
+                0.037477375030517575,
+                0.03746713638305664,
+                0.0375245132446289,
+                0.03748246383666992,
+                0.03753267288208008,
+                0.03751424026489258,
+                0.03758182525634766,
+                0.03750092697143555,
+                0.03756851196289063,
+                0.03751119995117187,
+                0.03762684631347656,
+                0.03748659133911133,
+                0.03758694458007812,
+                0.03750809478759766,
+                0.03763814544677734,
+                0.037548030853271484,
+                0.03765350341796875,
+                0.037544960021972655,
+                0.03766988754272461,
+                0.03751628875732422,
+                0.037615615844726565,
+                0.03752243041992188,
+                0.037667839050292966,
+                0.03755724716186523,
+                0.03767295837402344,
+                0.037548030853271484,
+                0.03771289443969727,
+                0.037572608947753904,
+                0.03767910385131836,
+                0.03760025787353516,
+                0.03759206390380859,
+                0.037591041564941405,
+                0.037599231719970705,
+                0.0375654411315918,
+                0.03760435104370117,
+                0.03760844802856445,
+                0.037684223175048825,
+                0.037612545013427735,
+                0.037631999969482424,
+                0.03758796691894531,
+                0.03763814544677734,
+                0.0376258544921875,
+                0.037661697387695314,
+                0.037601280212402347,
+                0.03776204681396484,
+                0.037645313262939455,
+                0.03768115234375,
+                0.037644287109375,
+                0.03771084976196289,
+                0.03769241714477539,
+                0.03768832015991211,
+                0.03767295837402344,
+                0.03776716613769531,
+                0.03763916778564453,
+                0.03769753646850586,
+                0.037667839050292966
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.364807603199885
+        },
+        "energy": null,
+        "efficiency": null
+    }
+}