AwAppp
/

benchmark_original_batch_size35

Transformers

Model card Files Files and versions

xet

Community

AwAppp commited on Mar 6, 2024

Commit

d895676

verified ·

1 Parent(s): 735cc6a

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": 1476.939776,
+            "max_vram": 15674.114048,
+            "max_reserved": 15189.671936,
+            "max_allocated": 15039.57248
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 0.04063008809283498,
+            "stdev": 9.76172995398282e-05,
+            "values": [
+                0.04138979339599609,
+                0.04110335922241211,
+                0.04110335922241211,
+                0.041083839416503905,
+                0.04105625534057617,
+                0.041199615478515625,
+                0.04084940719604492,
+                0.04111667251586914,
+                0.040799232482910154,
+                0.040612865447998046,
+                0.04062617492675781,
+                0.04060876846313476,
+                0.04069375991821289,
+                0.040612865447998046,
+                0.04067020797729492,
+                0.04064255905151367,
+                0.04073164749145508,
+                0.04062515258789062,
+                0.04067839813232422,
+                0.040662017822265625,
+                0.04065689468383789,
+                0.04063334274291992,
+                0.04065280151367188,
+                0.04067635345458984,
+                0.040630271911621094,
+                0.04060774230957031,
+                0.040621055603027346,
+                0.04060671997070313,
+                0.04069375991821289,
+                0.04062822341918945,
+                0.04064665603637695,
+                0.04063436889648438,
+                0.040610816955566405,
+                0.040629249572753906,
+                0.040653823852539066,
+                0.04065689468383789,
+                0.040622081756591794,
+                0.04060979080200195,
+                0.04064460754394531,
+                0.04066304016113281,
+                0.04063641738891602,
+                0.04064972686767578,
+                0.04061798477172852,
+                0.04061695861816406,
+                0.040619007110595705,
+                0.04062617492675781,
+                0.04067020797729492,
+                0.04057907104492187,
+                0.0406640625,
+                0.04065894317626953,
+                0.0406578254699707,
+                0.04061692810058594,
+                0.04061491012573242,
+                0.040581119537353515,
+                0.04060569763183594,
+                0.040583168029785156,
+                0.040632320404052735,
+                0.0406036491394043,
+                0.04061491012573242,
+                0.04054425430297852,
+                0.04062003326416016,
+                0.040599552154541016,
+                0.0405852165222168,
+                0.040592384338378903,
+                0.040632320404052735,
+                0.040643585205078124,
+                0.040619007110595705,
+                0.040576000213623044,
+                0.040633281707763674,
+                0.04063641738891602,
+                0.040619968414306644,
+                0.04057292938232422,
+                0.040622081756591794,
+                0.040599552154541016,
+                0.04061798477172852,
+                0.04061695861816406,
+                0.04059033584594727,
+                0.040612865447998046,
+                0.04062819290161133,
+                0.04060876846313476,
+                0.04059545516967773,
+                0.04059545516967773,
+                0.040612865447998046,
+                0.040597503662109374,
+                0.040637439727783206,
+                0.040648704528808595,
+                0.040643585205078124,
+                0.04062515258789062,
+                0.04067225646972656,
+                0.040622081756591794,
+                0.040651775360107424,
+                0.040602622985839845,
+                0.04059033584594727,
+                0.04060774230957031,
+                0.04060979080200195,
+                0.040629249572753906,
+                0.0406036491394043,
+                0.04064665603637695,
+                0.0405401611328125,
+                0.04056576156616211,
+                0.040623039245605466,
+                0.040627201080322264,
+                0.040635391235351564,
+                0.040613887786865234,
+                0.04061695861816406,
+                0.04060153579711914,
+                0.040586238861083986,
+                0.04063641738891602,
+                0.040613887786865234,
+                0.04064355087280273,
+                0.040586238861083986,
+                0.04060160064697266,
+                0.04060774230957031,
+                0.040637439727783206,
+                0.040583168029785156,
+                0.04061798477172852,
+                0.04058518218994141,
+                0.040621055603027346,
+                0.04064051055908203,
+                0.04061183929443359,
+                0.0405667839050293,
+                0.040612865447998046,
+                0.04061798477172852,
+                0.040570911407470704,
+                0.04061798477172852,
+                0.04058726501464844,
+                0.04058620834350586,
+                0.04057190322875977,
+                0.040600574493408204,
+                0.040586238861083986,
+                0.04063840103149414,
+                0.04058009719848633,
+                0.04060876846313476,
+                0.04059033584594727,
+                0.040621055603027346,
+                0.04062412643432617,
+                0.040612865447998046,
+                0.04060774230957031,
+                0.040619007110595705,
+                0.04060160064697266,
+                0.0405852165222168,
+                0.040599552154541016,
+                0.04063641738891602,
+                0.04059648132324219,
+                0.040597503662109374,
+                0.040613887786865234,
+                0.040643585205078124,
+                0.040667137145996096,
+                0.040648704528808595,
+                0.040591358184814456,
+                0.04061695861816406,
+                0.040578048706054685,
+                0.04064972686767578,
+                0.04059545516967773,
+                0.04063948822021484,
+                0.040569854736328126,
+                0.040632320404052735,
+                0.040551422119140625,
+                0.04063436889648438,
+                0.04058828735351563,
+                0.04060467147827149,
+                0.040594432830810545,
+                0.0406640625,
+                0.04063334274291992,
+                0.040615936279296876,
+                0.04061183929443359,
+                0.04060160064697266,
+                0.040594432830810545,
+                0.040619007110595705,
+                0.040648704528808595,
+                0.04060569763183594,
+                0.04056268692016601,
+                0.040599552154541016,
+                0.04057292938232422,
+                0.04056576156616211,
+                0.04056268692016601,
+                0.04056371307373047,
+                0.04054732894897461,
+                0.04059033584594727,
+                0.04061695861816406,
+                0.04061183929443359,
+                0.04061491012573242,
+                0.04059033584594727,
+                0.0405852165222168,
+                0.040581119537353515,
+                0.040592384338378903,
+                0.04055551910400391,
+                0.04056576156616211,
+                0.04056576156616211,
+                0.04060671997070313,
+                0.040600574493408204,
+                0.04060569763183594,
+                0.040653823852539066,
+                0.04059033584594727,
+                0.04055756759643555,
+                0.04057702255249023,
+                0.04059852981567383,
+                0.04060768127441406,
+                0.04064255905151367,
+                0.04065792083740234,
+                0.04064255905151367,
+                0.040615936279296876,
+                0.04061183929443359,
+                0.040665088653564455,
+                0.04066099166870117,
+                0.04061183929443359,
+                0.040653823852539066,
+                0.040615936279296876,
+                0.04059545516967773,
+                0.04058214569091797,
+                0.040632320404052735,
+                0.04060255813598633,
+                0.04060979080200195,
+                0.040574977874755856,
+                0.0406036491394043,
+                0.040643585205078124,
+                0.040583168029785156,
+                0.04059545516967773,
+                0.04058726501464844,
+                0.040594432830810545,
+                0.04058828735351563,
+                0.040618911743164066,
+                0.040581119537353515,
+                0.040553470611572266,
+                0.040586143493652346,
+                0.04060774230957031,
+                0.04065075302124024,
+                0.04056576156616211,
+                0.04061798477172852,
+                0.040612865447998046,
+                0.040615936279296876,
+                0.040613887786865234,
+                0.04067942428588867,
+                0.04064972686767578,
+                0.040612865447998046,
+                0.040610816955566405,
+                0.04062617492675781,
+                0.040630271911621094,
+                0.04064767837524414,
+                0.04057292938232422,
+                0.0405667839050293,
+                0.04055244827270508,
+                0.04056576156616211,
+                0.040594432830810545,
+                0.04058009719848633,
+                0.0405667839050293
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 787.5936652385237
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "decode": {
+        "memory": {
+            "unit": "MB",
+            "max_ram": 1488.171008,
+            "max_vram": 15739.12576,
+            "max_reserved": 15254.683648,
+            "max_allocated": 15101.761024
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 3.71086609395345,
+            "stdev": 5.97791248185428e-05,
+            "values": [
+                3.710939136505127,
+                3.7108664360046384,
+                3.7107927093505846
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.35681616823217
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "per_token": {
+        "memory": null,
+        "latency": {
+            "unit": "s",
+            "mean": 0.03748349589851969,
+            "stdev": 0.00015874297262972117,
+            "values": [
+                0.03729715347290039,
+                0.03720806503295898,
+                0.03720294570922852,
+                0.03721420669555664,
+                0.03719782257080078,
+                0.03722444915771484,
+                0.037253120422363284,
+                0.037256191253662106,
+                0.03727974319458008,
+                0.03727052688598633,
+                0.03727155303955078,
+                0.03725823974609375,
+                0.03727052688598633,
+                0.03731353759765625,
+                0.03729100799560547,
+                0.03726335906982422,
+                0.037318656921386716,
+                0.037294078826904296,
+                0.03727667236328125,
+                0.03733913421630859,
+                0.0373043212890625,
+                0.0373125114440918,
+                0.03729919815063477,
+                0.03727872085571289,
+                0.03727667236328125,
+                0.03737190246582031,
+                0.03733401489257813,
+                0.03740467071533203,
+                0.037356544494628906,
+                0.03736064147949219,
+                0.03736064147949219,
+                0.03744460678100586,
+                0.03737395095825195,
+                0.037384193420410154,
+                0.037410816192626956,
+                0.03739852905273437,
+                0.03744460678100586,
+                0.037466110229492186,
+                0.03740262222290039,
+                0.037501953125,
+                0.037443584442138675,
+                0.03747532653808594,
+                0.03743436813354492,
+                0.03746713638305664,
+                0.03748044967651367,
+                0.037539840698242184,
+                0.03745280075073242,
+                0.03751116943359375,
+                0.03747430419921875,
+                0.03758694458007812,
+                0.03750297546386719,
+                0.037564414978027344,
+                0.037482494354248046,
+                0.03763916778564453,
+                0.037498878479003905,
+                0.03761151885986328,
+                0.03753062438964844,
+                0.03763507080078125,
+                0.03751321411132812,
+                0.037596160888671876,
+                0.037515262603759765,
+                0.03769753646850586,
+                0.03753267288208008,
+                0.037647361755371096,
+                0.03751731109619141,
+                0.03766886520385742,
+                0.037526527404785154,
+                0.03766886520385742,
+                0.03758694458007812,
+                0.03770470428466797,
+                0.03758899307250976,
+                0.03763916778564453,
+                0.0375838737487793,
+                0.03760844802856445,
+                0.03760332870483398,
+                0.03761971282958984,
+                0.037601280212402347,
+                0.03761151885986328,
+                0.03762790298461914,
+                0.037644287109375,
+                0.037572608947753904,
+                0.037615615844726565,
+                0.037602302551269534,
+                0.037618686676025394,
+                0.037618686676025394,
+                0.037631999969482424,
+                0.03761459350585938,
+                0.03777536010742188,
+                0.03766886520385742,
+                0.03768320083618164,
+                0.03765760040283203,
+                0.03765760040283203,
+                0.03769343948364258,
+                0.0376995849609375,
+                0.037663745880126956,
+                0.037765121459960936,
+                0.03765043258666992,
+                0.03769139099121094,
+                0.03763507080078125,
+                0.03720806503295898,
+                0.03717222213745117,
+                0.037207038879394534,
+                0.03724697494506836,
+                0.03723161697387695,
+                0.037217281341552735,
+                0.03722444915771484,
+                0.03721932983398438,
+                0.03723161697387695,
+                0.03730022430419922,
+                0.03725721740722656,
+                0.03727155303955078,
+                0.03732889556884766,
+                0.03729100799560547,
+                0.03727360153198242,
+                0.03725414276123047,
+                0.037302272796630856,
+                0.03734732818603516,
+                0.03729612731933594,
+                0.03731660842895508,
+                0.03726131057739258,
+                0.0373309440612793,
+                0.03729305648803711,
+                0.03732582473754883,
+                0.03728998565673828,
+                0.03738214492797851,
+                0.037324798583984374,
+                0.037378047943115236,
+                0.03734425735473633,
+                0.03738214492797851,
+                0.0373493766784668,
+                0.037408767700195314,
+                0.03737190246582031,
+                0.03740671920776367,
+                0.03736678314208984,
+                0.03738726425170898,
+                0.0374466552734375,
+                0.037449726104736326,
+                0.03738726425170898,
+                0.037493759155273435,
+                0.037410816192626956,
+                0.03750400161743164,
+                0.03746713638305664,
+                0.03746918487548828,
+                0.03747020721435547,
+                0.03752959823608398,
+                0.03743231964111328,
+                0.0375203857421875,
+                0.03745177459716797,
+                0.03760435104370117,
+                0.037495807647705076,
+                0.037602302551269534,
+                0.03749068832397461,
+                0.037607425689697264,
+                0.03749990463256836,
+                0.037601280212402347,
+                0.03748556900024414,
+                0.037678081512451174,
+                0.0375203857421875,
+                0.037594112396240234,
+                0.037525505065917966,
+                0.03769036865234375,
+                0.037515262603759765,
+                0.037618686676025394,
+                0.037512191772460936,
+                0.03768115234375,
+                0.03750092697143555,
+                0.03768524932861328,
+                0.037569534301757815,
+                0.03774054336547852,
+                0.03757567977905273,
+                0.037661697387695314,
+                0.03756032180786133,
+                0.03762073516845703,
+                0.03756748962402344,
+                0.03762483215332031,
+                0.03758182525634766,
+                0.03762176132202148,
+                0.037585918426513674,
+                0.03767705535888672,
+                0.037602302551269534,
+                0.03764223861694336,
+                0.037612545013427735,
+                0.03769651031494141,
+                0.03763916778564453,
+                0.037684223175048825,
+                0.03758489608764649,
+                0.037754878997802735,
+                0.037574657440185545,
+                0.03766579055786133,
+                0.03764223861694336,
+                0.03769241714477539,
+                0.03767705535888672,
+                0.037700607299804685,
+                0.03768524932861328,
+                0.03781631851196289,
+                0.03766988754272461,
+                0.0377262077331543,
+                0.03766886520385742,
+                0.03723775863647461,
+                0.03718656158447266,
+                0.037250049591064455,
+                0.03724390411376953,
+                0.03722444915771484,
+                0.03726233673095703,
+                0.037200897216796876,
+                0.03725209426879883,
+                0.037222400665283206,
+                0.037282817840576174,
+                0.03721830368041992,
+                0.03726847839355469,
+                0.03725107192993164,
+                0.03729100799560547,
+                0.03727974319458008,
+                0.03727052688598633,
+                0.037282817840576174,
+                0.037292030334472655,
+                0.03728076934814453,
+                0.037318656921386716,
+                0.03732582473754883,
+                0.037335041046142575,
+                0.03731455993652344,
+                0.03734220886230469,
+                0.037348350524902346,
+                0.037318656921386716,
+                0.037302272796630856,
+                0.0373493766784668,
+                0.037338111877441404,
+                0.03737395095825195,
+                0.03737190246582031,
+                0.03741798400878906,
+                0.03738521575927734,
+                0.03740467071533203,
+                0.03737395095825195,
+                0.03740364837646484,
+                0.03737190246582031,
+                0.03741798400878906,
+                0.037394432067871096,
+                0.037495807647705076,
+                0.03741183853149414,
+                0.03748761749267578,
+                0.037459968566894535,
+                0.03748556900024414,
+                0.03750092697143555,
+                0.03752345657348633,
+                0.03749478530883789,
+                0.037539840698242184,
+                0.03747840118408203,
+                0.03760435104370117,
+                0.03750502395629883,
+                0.0376258544921875,
+                0.03751935958862305,
+                0.0376545295715332,
+                0.03750297546386719,
+                0.03758182525634766,
+                0.03751116943359375,
+                0.037628929138183595,
+                0.03747430419921875,
+                0.03763507080078125,
+                0.037533695220947266,
+                0.03763097763061524,
+                0.03753062438964844,
+                0.03759820938110352,
+                0.0375623664855957,
+                0.03763916778564453,
+                0.037558273315429686,
+                0.03766067123413086,
+                0.03753779220581055,
+                0.03771084976196289,
+                0.03758182525634766,
+                0.03766886520385742,
+                0.037572608947753904,
+                0.03761356735229492,
+                0.03763507080078125,
+                0.03762073516845703,
+                0.037582847595214845,
+                0.03763302230834961,
+                0.037585918426513674,
+                0.03767500686645508,
+                0.03758489608764649,
+                0.037585918426513674,
+                0.037602302551269534,
+                0.03762995147705078,
+                0.03764326477050781,
+                0.037628929138183595,
+                0.03763302230834961,
+                0.03772723388671875,
+                0.03761356735229492,
+                0.03769651031494141,
+                0.037661697387695314,
+                0.03767910385131836,
+                0.03765350341796875,
+                0.03765760040283203,
+                0.037663745880126956,
+                0.037720062255859374,
+                0.03770265579223633,
+                0.03772723388671875,
+                0.03772108840942383
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.356816168232186
+        },
+        "energy": null,
+        "efficiency": null
+    }
+}