AwAppp
/

benchmark_original_batch_size5

Transformers

Model card Files Files and versions

xet

Community

AwAppp commited on Mar 6, 2024

Commit

43d76f4

verified ·

1 Parent(s): 3b9da9f

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": 1476.288512,
+            "max_vram": 15674.114048,
+            "max_reserved": 15189.671936,
+            "max_allocated": 15039.57248
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 0.04063447015653783,
+            "stdev": 0.00010095564261546599,
+            "values": [
+                0.041492897033691405,
+                0.04113404846191406,
+                0.04114329528808594,
+                0.041093120574951174,
+                0.04108390426635742,
+                0.04109107208251953,
+                0.04096716690063477,
+                0.04110335922241211,
+                0.040852481842041016,
+                0.040612865447998046,
+                0.04064972686767578,
+                0.040597503662109374,
+                0.04065792083740234,
+                0.040645633697509766,
+                0.04066099166870117,
+                0.04061692810058594,
+                0.040653823852539066,
+                0.040637439727783206,
+                0.04067023849487305,
+                0.04066304016113281,
+                0.040622081756591794,
+                0.040622081756591794,
+                0.04063641738891602,
+                0.04062003326416016,
+                0.040659969329833984,
+                0.04062515258789062,
+                0.04065075302124024,
+                0.04057491302490234,
+                0.04063334274291992,
+                0.040643585205078124,
+                0.040703998565673825,
+                0.040619007110595705,
+                0.04061993789672851,
+                0.040645633697509766,
+                0.040635391235351564,
+                0.040680416107177736,
+                0.04062515258789062,
+                0.040635391235351564,
+                0.04059545516967773,
+                0.04067225646972656,
+                0.04070809555053711,
+                0.04068966293334961,
+                0.040615936279296876,
+                0.04065075302124024,
+                0.040627201080322264,
+                0.04063641738891602,
+                0.04063436889648438,
+                0.040613887786865234,
+                0.040612865447998046,
+                0.040671230316162106,
+                0.04064255905151367,
+                0.04062003326416016,
+                0.04059743881225586,
+                0.04057395172119141,
+                0.040612865447998046,
+                0.04061491012573242,
+                0.040637439727783206,
+                0.040622081756591794,
+                0.040591358184814456,
+                0.040545280456542966,
+                0.04061183929443359,
+                0.040652736663818356,
+                0.04062412643432617,
+                0.040615936279296876,
+                0.04058726501464844,
+                0.04062617492675781,
+                0.04061183929443359,
+                0.040592384338378903,
+                0.040632320404052735,
+                0.040643585205078124,
+                0.04063846588134765,
+                0.04062310409545898,
+                0.04063436889648438,
+                0.04059545516967773,
+                0.040622081756591794,
+                0.04062515258789062,
+                0.0405852165222168,
+                0.040629249572753906,
+                0.04062003326416016,
+                0.040629249572753906,
+                0.04062003326416016,
+                0.04060569763183594,
+                0.040610816955566405,
+                0.04060671997070313,
+                0.040648704528808595,
+                0.04066304016113281,
+                0.04064972686767578,
+                0.04064972686767578,
+                0.04060569763183594,
+                0.04064767837524414,
+                0.04065792083740234,
+                0.040651775360107424,
+                0.04062310409545898,
+                0.04058726501464844,
+                0.04062822341918945,
+                0.04063846588134765,
+                0.04064153671264648,
+                0.040637439727783206,
+                0.04055756759643555,
+                0.04060876846313476,
+                0.040635391235351564,
+                0.04063948822021484,
+                0.04065792083740234,
+                0.04062515258789062,
+                0.04061183929443359,
+                0.040599552154541016,
+                0.040602622985839845,
+                0.04058931350708008,
+                0.04064153671264648,
+                0.040632320404052735,
+                0.040602622985839845,
+                0.0405852165222168,
+                0.04059340667724609,
+                0.040653823852539066,
+                0.04061183929443359,
+                0.04060979080200195,
+                0.04062617492675781,
+                0.04058931350708008,
+                0.04064051055908203,
+                0.04061183929443359,
+                0.04058009719848633,
+                0.040602622985839845,
+                0.040637439727783206,
+                0.040629249572753906,
+                0.040637439727783206,
+                0.04060160064697266,
+                0.040630271911621094,
+                0.040586238861083986,
+                0.04063129425048828,
+                0.04063638305664063,
+                0.04062412643432617,
+                0.04060774230957031,
+                0.04059545516967773,
+                0.040600574493408204,
+                0.04058931350708008,
+                0.040635391235351564,
+                0.04057692718505859,
+                0.040591327667236325,
+                0.04059033584594727,
+                0.04062617492675781,
+                0.04060979080200195,
+                0.04058313751220703,
+                0.040592384338378903,
+                0.04063948822021484,
+                0.04064255905151367,
+                0.040613887786865234,
+                0.04064665603637695,
+                0.0406363525390625,
+                0.040619007110595705,
+                0.04061491012573242,
+                0.040622081756591794,
+                0.0405667839050293,
+                0.04064972686767578,
+                0.040576000213623044,
+                0.04066099166870117,
+                0.04059648132324219,
+                0.04063948822021484,
+                0.04056883239746094,
+                0.04063641738891602,
+                0.040597503662109374,
+                0.040599552154541016,
+                0.04057292938232422,
+                0.040608673095703124,
+                0.04064051055908203,
+                0.04060160064697266,
+                0.04059340667724609,
+                0.04064153671264648,
+                0.04059545516967773,
+                0.040612865447998046,
+                0.040622081756591794,
+                0.0405852165222168,
+                0.040591358184814456,
+                0.04059852981567383,
+                0.040600574493408204,
+                0.04059852981567383,
+                0.04066099166870117,
+                0.04055654525756836,
+                0.040581119537353515,
+                0.040613887786865234,
+                0.040578048706054685,
+                0.04060979080200195,
+                0.04060467147827149,
+                0.04058726501464844,
+                0.04061075210571289,
+                0.04060467147827149,
+                0.04060467147827149,
+                0.04058214569091797,
+                0.040578048706054685,
+                0.04055551910400391,
+                0.040621055603027346,
+                0.0405852165222168,
+                0.04063846588134765,
+                0.04064255905151367,
+                0.04058828735351563,
+                0.04057088088989258,
+                0.040546302795410154,
+                0.040600574493408204,
+                0.04062412643432617,
+                0.04066304016113281,
+                0.040627201080322264,
+                0.04064255905151367,
+                0.040630271911621094,
+                0.040629249572753906,
+                0.04061695861816406,
+                0.04061695861816406,
+                0.040602622985839845,
+                0.04060873413085937,
+                0.040621055603027346,
+                0.040635391235351564,
+                0.04060876846313476,
+                0.0406036491394043,
+                0.04060876846313476,
+                0.04061695861816406,
+                0.04058009719848633,
+                0.040621055603027346,
+                0.04062310409545898,
+                0.040600574493408204,
+                0.040600574493408204,
+                0.04058726501464844,
+                0.040621055603027346,
+                0.040627201080322264,
+                0.04057702255249023,
+                0.0406036491394043,
+                0.04057395172119141,
+                0.04058726501464844,
+                0.04060876846313476,
+                0.04061491012573242,
+                0.040576000213623044,
+                0.040584190368652344,
+                0.040599552154541016,
+                0.04061798477172852,
+                0.04061183929443359,
+                0.040667137145996096,
+                0.04061798477172852,
+                0.040602622985839845,
+                0.04062412643432617,
+                0.040622081756591794,
+                0.040637439727783206,
+                0.04061798477172852,
+                0.040599552154541016,
+                0.040551422119140625,
+                0.040591327667236325,
+                0.04056876754760742,
+                0.040594432830810545,
+                0.04053606414794922,
+                0.040602622985839845
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 787.5087303150525
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "decode": {
+        "memory": {
+            "unit": "MB",
+            "max_ram": 1487.204352,
+            "max_vram": 15739.12576,
+            "max_reserved": 15254.683648,
+            "max_allocated": 15101.761024
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 3.708370947519938,
+            "stdev": 0.00019802779189991205,
+            "values": [
+                3.7080985488891582,
+                3.708450828552247,
+                3.7085634651184085
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.392716856553214
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "per_token": {
+        "memory": null,
+        "latency": {
+            "unit": "s",
+            "mean": 0.03745829239919128,
+            "stdev": 0.00015786611458293046,
+            "values": [
+                0.03724390411376953,
+                0.037177345275878904,
+                0.037190654754638675,
+                0.037195777893066405,
+                0.03715584182739258,
+                0.037212158203125,
+                0.037253120422363284,
+                0.03718041610717773,
+                0.03724390411376953,
+                0.03727462387084961,
+                0.03723775863647461,
+                0.03725823974609375,
+                0.03727360153198242,
+                0.037303295135498044,
+                0.03725516891479492,
+                0.03725823974609375,
+                0.037292030334472655,
+                0.03728793716430664,
+                0.03724595260620117,
+                0.03731455993652344,
+                0.037256191253662106,
+                0.03729715347290039,
+                0.03729100799560547,
+                0.037266433715820314,
+                0.037275646209716795,
+                0.037356544494628906,
+                0.03729919815063477,
+                0.037340160369873046,
+                0.03734220886230469,
+                0.03733196640014649,
+                0.037370880126953124,
+                0.0374200325012207,
+                0.03729919815063477,
+                0.03736883163452148,
+                0.03737702560424805,
+                0.037392383575439454,
+                0.03737395095825195,
+                0.03741900634765625,
+                0.037343231201171875,
+                0.03745177459716797,
+                0.03739648056030274,
+                0.03746406555175781,
+                0.03738828659057617,
+                0.03746918487548828,
+                0.0374128646850586,
+                0.03745894241333008,
+                0.03744870376586914,
+                0.03753779220581055,
+                0.037477375030517575,
+                0.037566463470458986,
+                0.03744563293457031,
+                0.0375838737487793,
+                0.03743129730224609,
+                0.03764019012451172,
+                0.03747020721435547,
+                0.03760435104370117,
+                0.03750604629516602,
+                0.03760537719726562,
+                0.03744255828857422,
+                0.03759001541137695,
+                0.03748147201538086,
+                0.03766886520385742,
+                0.037482494354248046,
+                0.03757567977905273,
+                0.037495807647705076,
+                0.03762278366088867,
+                0.03753267288208008,
+                0.03764121627807617,
+                0.03757363128662109,
+                0.03768832015991211,
+                0.03757567977905273,
+                0.03763507080078125,
+                0.03753676986694336,
+                0.0375623664855957,
+                0.03753062438964844,
+                0.03753062438964844,
+                0.03755417633056641,
+                0.03759718322753906,
+                0.0375470085144043,
+                0.03764940643310547,
+                0.03754905700683594,
+                0.03759308624267578,
+                0.037628929138183595,
+                0.03758694458007812,
+                0.037596160888671876,
+                0.03761356735229492,
+                0.03760435104370117,
+                0.03770675277709961,
+                0.03762995147705078,
+                0.03764019012451172,
+                0.03758489608764649,
+                0.037664768218994144,
+                0.03760537719726562,
+                0.03767193603515625,
+                0.03761356735229492,
+                0.03772825622558594,
+                0.03763302230834961,
+                0.03767193603515625,
+                0.03762688064575195,
+                0.03716198348999023,
+                0.03719987106323242,
+                0.03719475173950195,
+                0.037177345275878904,
+                0.03721011352539062,
+                0.03721113586425781,
+                0.03720499038696289,
+                0.03719372940063476,
+                0.037238784790039066,
+                0.03726233673095703,
+                0.03727667236328125,
+                0.037282817840576174,
+                0.03722444915771484,
+                0.03724288177490234,
+                0.037250049591064455,
+                0.037223423004150394,
+                0.03725516891479492,
+                0.03727769470214844,
+                0.037272575378417966,
+                0.03726335906982422,
+                0.03723468780517578,
+                0.0373043212890625,
+                0.03721420669555664,
+                0.03729612731933594,
+                0.03732582473754883,
+                0.03737497711181641,
+                0.03732275390625,
+                0.03734425735473633,
+                0.03732787322998047,
+                0.037372928619384765,
+                0.037356544494628906,
+                0.037392383575439454,
+                0.037369857788085936,
+                0.037362686157226564,
+                0.03733913421630859,
+                0.037375999450683595,
+                0.03744460678100586,
+                0.03740671920776367,
+                0.037379070281982424,
+                0.0374466552734375,
+                0.0373831672668457,
+                0.037443584442138675,
+                0.037395454406738284,
+                0.03747840118408203,
+                0.03745894241333008,
+                0.03748863983154297,
+                0.03744768142700195,
+                0.03749990463256836,
+                0.03744870376586914,
+                0.03758694458007812,
+                0.037443584442138675,
+                0.037533695220947266,
+                0.03747840118408203,
+                0.03759001541137695,
+                0.03748761749267578,
+                0.03757363128662109,
+                0.037449726104736326,
+                0.03764121627807617,
+                0.037479423522949216,
+                0.03758796691894531,
+                0.03750502395629883,
+                0.03767705535888672,
+                0.03748556900024414,
+                0.03758796691894531,
+                0.03746918487548828,
+                0.0376360969543457,
+                0.037533695220947266,
+                0.03768832015991211,
+                0.037531646728515625,
+                0.03768832015991211,
+                0.037550079345703126,
+                0.03765760040283203,
+                0.03755929565429687,
+                0.03762483215332031,
+                0.03758899307250976,
+                0.03760639953613281,
+                0.03757567977905273,
+                0.03758899307250976,
+                0.03760435104370117,
+                0.03766579055786133,
+                0.03756032180786133,
+                0.037579776763916016,
+                0.03762176132202148,
+                0.03760332870483398,
+                0.0375838737487793,
+                0.037667839050292966,
+                0.037596160888671876,
+                0.037705726623535156,
+                0.03760332870483398,
+                0.03764326477050781,
+                0.037582847595214845,
+                0.037719039916992186,
+                0.03760025787353516,
+                0.03768729782104492,
+                0.037661697387695314,
+                0.03774054336547852,
+                0.037634048461914066,
+                0.03769241714477539,
+                0.03762995147705078,
+                0.037217281341552735,
+                0.037169151306152344,
+                0.037177345275878904,
+                0.037220352172851565,
+                0.03719987106323242,
+                0.03722956848144531,
+                0.037223423004150394,
+                0.0372592658996582,
+                0.03719475173950195,
+                0.037250049591064455,
+                0.03720499038696289,
+                0.03724697494506836,
+                0.03721625518798828,
+                0.03730636978149414,
+                0.037233665466308595,
+                0.03725516891479492,
+                0.03724800109863281,
+                0.037269504547119144,
+                0.03724697494506836,
+                0.037292030334472655,
+                0.037272575378417966,
+                0.037302272796630856,
+                0.03727769470214844,
+                0.037303295135498044,
+                0.03728179168701172,
+                0.037343231201171875,
+                0.03729919815063477,
+                0.03734425735473633,
+                0.03731148910522461,
+                0.037370880126953124,
+                0.03737497711181641,
+                0.03739648056030274,
+                0.0373831672668457,
+                0.037395454406738284,
+                0.037364734649658206,
+                0.03740879821777344,
+                0.03738211059570312,
+                0.03741798400878906,
+                0.03738009643554688,
+                0.03743436813354492,
+                0.03745177459716797,
+                0.03745177459716797,
+                0.037389312744140625,
+                0.03745075225830078,
+                0.03742924880981445,
+                0.0375470085144043,
+                0.03745792007446289,
+                0.03748761749267578,
+                0.03749068832397461,
+                0.03755110549926758,
+                0.03745792007446289,
+                0.03759206390380859,
+                0.03745587158203125,
+                0.0376360969543457,
+                0.037482494354248046,
+                0.03755110549926758,
+                0.03750707244873047,
+                0.03761151885986328,
+                0.03746201705932617,
+                0.03758899307250976,
+                0.03749785614013672,
+                0.037634048461914066,
+                0.03749273681640625,
+                0.03759820938110352,
+                0.0375203857421875,
+                0.03759513473510742,
+                0.037553150177001955,
+                0.03765350341796875,
+                0.03755724716186523,
+                0.037698558807373043,
+                0.037525505065917966,
+                0.037634048461914066,
+                0.03755724716186523,
+                0.037582847595214845,
+                0.03757567977905273,
+                0.037582847595214845,
+                0.03756851196289063,
+                0.037594112396240234,
+                0.037556224822998044,
+                0.03765555191040039,
+                0.037558273315429686,
+                0.037647361755371096,
+                0.03754905700683594,
+                0.037615615844726565,
+                0.037607425689697264,
+                0.037623809814453124,
+                0.03764633560180664,
+                0.03770265579223633,
+                0.037599231719970705,
+                0.03765555191040039,
+                0.0375838737487793,
+                0.037689342498779296,
+                0.03759820938110352,
+                0.03766579055786133,
+                0.03766681671142578,
+                0.03773952102661133,
+                0.03765760040283203,
+                0.03768012619018555,
+                0.03768524932861328
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.39271685655323
+        },
+        "energy": null,
+        "efficiency": null
+    }
+}