AwAppp
/

benchmark_original_batch_size10

Transformers

Model card Files Files and versions

xet

Community

AwAppp commited on Mar 6, 2024

Commit

d3db98a

verified ·

1 Parent(s): 07a97e7

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": 1476.665344,
+            "max_vram": 15674.114048,
+            "max_reserved": 15189.671936,
+            "max_allocated": 15039.57248
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 0.040603640750171685,
+            "stdev": 0.00010272403794894722,
+            "values": [
+                0.04150588989257813,
+                0.041099262237548825,
+                0.04108083343505859,
+                0.041046016693115236,
+                0.041059326171875,
+                0.04103680038452148,
+                0.041040897369384766,
+                0.04108486557006836,
+                0.04070195388793945,
+                0.040600574493408204,
+                0.04060979080200195,
+                0.040619007110595705,
+                0.04062617492675781,
+                0.04057907104492187,
+                0.04058931350708008,
+                0.040612831115722656,
+                0.040643585205078124,
+                0.04059033584594727,
+                0.04063641738891602,
+                0.04063948822021484,
+                0.040600574493408204,
+                0.04063129425048828,
+                0.040622081756591794,
+                0.04060876846313476,
+                0.04061491012573242,
+                0.04060774230957031,
+                0.040592384338378903,
+                0.04062412643432617,
+                0.04067225646972656,
+                0.040635391235351564,
+                0.04062819290161133,
+                0.04060569763183594,
+                0.04060467147827149,
+                0.040622081756591794,
+                0.04063436889648438,
+                0.040602622985839845,
+                0.04059033584594727,
+                0.04055449676513672,
+                0.040612865447998046,
+                0.04063846588134765,
+                0.04060467147827149,
+                0.040599552154541016,
+                0.04057088088989258,
+                0.040578048706054685,
+                0.040578048706054685,
+                0.040584190368652344,
+                0.040671230316162106,
+                0.040592384338378903,
+                0.04060671997070313,
+                0.04064767837524414,
+                0.04061798477172852,
+                0.04059033584594727,
+                0.040569854736328126,
+                0.040548351287841795,
+                0.04056883239746094,
+                0.04058931350708008,
+                0.04058931350708008,
+                0.04056883239746094,
+                0.040597503662109374,
+                0.04053401565551758,
+                0.040574977874755856,
+                0.04057395172119141,
+                0.04055859375,
+                0.04056883239746094,
+                0.04058726501464844,
+                0.04060569763183594,
+                0.04057088088989258,
+                0.040567806243896484,
+                0.04061183929443359,
+                0.0406416015625,
+                0.04059852981567383,
+                0.040612865447998046,
+                0.04062003326416016,
+                0.04057292938232422,
+                0.04057699203491211,
+                0.0406743049621582,
+                0.04055446243286133,
+                0.04056268692016601,
+                0.04059545516967773,
+                0.04056268692016601,
+                0.040591358184814456,
+                0.04060467147827149,
+                0.04057807922363281,
+                0.04058726501464844,
+                0.04063334274291992,
+                0.04060979080200195,
+                0.040635391235351564,
+                0.04063129425048828,
+                0.04056883239746094,
+                0.040574977874755856,
+                0.040630271911621094,
+                0.040583168029785156,
+                0.040597503662109374,
+                0.040569854736328126,
+                0.040592384338378903,
+                0.040576000213623044,
+                0.040594432830810545,
+                0.04060569763183594,
+                0.040546302795410154,
+                0.04056268692016601,
+                0.04057699203491211,
+                0.04063334274291992,
+                0.040632320404052735,
+                0.04059648132324219,
+                0.04056268692016601,
+                0.040584190368652344,
+                0.04056576156616211,
+                0.04060774230957031,
+                0.04058828735351563,
+                0.040649665832519534,
+                0.04056371307373047,
+                0.04056979370117188,
+                0.04055654525756836,
+                0.040574977874755856,
+                0.04055859375,
+                0.040612865447998046,
+                0.04056268692016601,
+                0.040584190368652344,
+                0.04058214569091797,
+                0.040602622985839845,
+                0.0405667839050293,
+                0.040629249572753906,
+                0.040581119537353515,
+                0.04055551910400391,
+                0.04056883239746094,
+                0.0405852165222168,
+                0.04058515167236328,
+                0.040600574493408204,
+                0.04056883239746094,
+                0.04056371307373047,
+                0.04059545516967773,
+                0.04056268692016601,
+                0.0405667839050293,
+                0.04057088088989258,
+                0.040548351287841795,
+                0.04058828735351563,
+                0.040578048706054685,
+                0.040567806243896484,
+                0.040583168029785156,
+                0.04060467147827149,
+                0.040546302795410154,
+                0.0405667839050293,
+                0.040586238861083986,
+                0.04060160064697266,
+                0.040627201080322264,
+                0.04063948822021484,
+                0.04062412643432617,
+                0.040612865447998046,
+                0.040612865447998046,
+                0.040561664581298826,
+                0.04056883239746094,
+                0.04056268692016601,
+                0.04058828735351563,
+                0.04051148986816406,
+                0.04062515258789062,
+                0.040583168029785156,
+                0.04059033584594727,
+                0.040548351287841795,
+                0.04057088088989258,
+                0.04057190322875977,
+                0.04057696151733398,
+                0.04055551910400391,
+                0.040635391235351564,
+                0.04057292938232422,
+                0.04056268692016601,
+                0.04057292938232422,
+                0.04055654525756836,
+                0.04058726501464844,
+                0.04057696151733398,
+                0.0405852165222168,
+                0.04055654525756836,
+                0.04055859375,
+                0.04058009719848633,
+                0.04058726501464844,
+                0.04056883239746094,
+                0.040546302795410154,
+                0.04052684783935547,
+                0.040546302795410154,
+                0.04058726501464844,
+                0.04057190322875977,
+                0.04058828735351563,
+                0.04054832077026367,
+                0.040567806243896484,
+                0.04057702255249023,
+                0.040567806243896484,
+                0.04055859375,
+                0.040546302795410154,
+                0.040542209625244144,
+                0.04056063842773437,
+                0.04060979080200195,
+                0.0405667839050293,
+                0.04059340667724609,
+                0.04059545516967773,
+                0.040542209625244144,
+                0.04054937744140625,
+                0.0405401611328125,
+                0.040553470611572266,
+                0.04059648132324219,
+                0.04059852981567383,
+                0.040648704528808595,
+                0.040632320404052735,
+                0.04057907104492187,
+                0.04060569763183594,
+                0.04060569763183594,
+                0.04060979080200195,
+                0.04060671997070313,
+                0.04057190322875977,
+                0.04058931350708008,
+                0.04053395080566406,
+                0.040584190368652344,
+                0.04057088088989258,
+                0.04057699203491211,
+                0.040594432830810545,
+                0.04057907104492187,
+                0.04057702255249023,
+                0.040621055603027346,
+                0.040594432830810545,
+                0.040551422119140625,
+                0.040548351287841795,
+                0.04059648132324219,
+                0.04055654525756836,
+                0.04057699203491211,
+                0.04053606414794922,
+                0.040545280456542966,
+                0.0405667839050293,
+                0.04054425430297852,
+                0.04057190322875977,
+                0.04055039978027344,
+                0.04053094482421875,
+                0.040567806243896484,
+                0.04059340667724609,
+                0.04058310317993164,
+                0.04063334274291992,
+                0.040629249572753906,
+                0.04058726501464844,
+                0.040567806243896484,
+                0.040567806243896484,
+                0.04059545516967773,
+                0.0405810546875,
+                0.04056883239746094,
+                0.040503231048583985,
+                0.040548351287841795,
+                0.040527809143066404,
+                0.04055756759643555,
+                0.04055039978027344,
+                0.040545280456542966
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 788.1066675003692
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "decode": {
+        "memory": {
+            "unit": "MB",
+            "max_ram": 1487.515648,
+            "max_vram": 15739.12576,
+            "max_reserved": 15254.683648,
+            "max_allocated": 15101.761024
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 3.7061430625915524,
+            "stdev": 0.0004980685782824457,
+            "values": [
+                3.705805835723877,
+                3.705776123046874,
+                3.7068472290039054
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.42481298105821
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "per_token": {
+        "memory": null,
+        "latency": {
+            "unit": "s",
+            "mean": 0.03743578851102577,
+            "stdev": 0.0001575827338807445,
+            "values": [
+                0.037220352172851565,
+                0.03719680023193359,
+                0.037154815673828126,
+                0.037185535430908204,
+                0.03719580841064453,
+                0.03720291137695313,
+                0.0371701774597168,
+                0.037160961151123044,
+                0.03719680023193359,
+                0.03721011352539062,
+                0.0372305908203125,
+                0.03724288177490234,
+                0.03720806503295898,
+                0.03727462387084961,
+                0.03731660842895508,
+                0.03725721740722656,
+                0.03722143936157227,
+                0.03725203323364258,
+                0.03722649765014648,
+                0.037253120422363284,
+                0.03725107192993164,
+                0.037310462951660156,
+                0.03722649765014648,
+                0.03725823974609375,
+                0.037253120422363284,
+                0.03728793716430664,
+                0.03727667236328125,
+                0.03733401489257813,
+                0.03727360153198242,
+                0.03732889556884766,
+                0.037340160369873046,
+                0.03734732818603516,
+                0.03732889556884766,
+                0.03734630584716797,
+                0.037343231201171875,
+                0.037369857788085936,
+                0.03735551834106445,
+                0.03737702560424805,
+                0.03736576080322265,
+                0.03743436813354492,
+                0.03738521575927734,
+                0.03744153594970703,
+                0.03738521575927734,
+                0.03743129730224609,
+                0.03743334579467773,
+                0.037501953125,
+                0.03741183853149414,
+                0.03751628875732422,
+                0.03740262222290039,
+                0.037548030853271484,
+                0.03744153594970703,
+                0.03753881454467774,
+                0.03740364837646484,
+                0.037607425689697264,
+                0.037438465118408204,
+                0.03755724716186523,
+                0.03743948745727539,
+                0.03760537719726562,
+                0.03747123336791992,
+                0.03755724716186523,
+                0.03745177459716797,
+                0.03763507080078125,
+                0.03745587158203125,
+                0.037553150177001955,
+                0.03747123336791992,
+                0.037628929138183595,
+                0.037512191772460936,
+                0.037601280212402347,
+                0.03750400161743164,
+                0.037644287109375,
+                0.03754291152954101,
+                0.03761459350585938,
+                0.03752447891235351,
+                0.03756851196289063,
+                0.0374958381652832,
+                0.03754800033569336,
+                0.03755417633056641,
+                0.03759206390380859,
+                0.037533695220947266,
+                0.037634048461914066,
+                0.03753062438964844,
+                0.037572608947753904,
+                0.03756748962402344,
+                0.03757363128662109,
+                0.037558273315429686,
+                0.037563392639160156,
+                0.037580799102783204,
+                0.03767705535888672,
+                0.03755929565429687,
+                0.03762278366088867,
+                0.0375623664855957,
+                0.03762278366088867,
+                0.03756851196289063,
+                0.037648384094238284,
+                0.03764121627807617,
+                0.03772927856445313,
+                0.03761356735229492,
+                0.037618686676025394,
+                0.03762483215332031,
+                0.037149696350097655,
+                0.03717836761474609,
+                0.037175361633300784,
+                0.03716089630126953,
+                0.037166080474853515,
+                0.03717836761474609,
+                0.0371599349975586,
+                0.03724390411376953,
+                0.03721932983398438,
+                0.03721318435668945,
+                0.03719987106323242,
+                0.03724800109863281,
+                0.03720806503295898,
+                0.03725107192993164,
+                0.03725209426879883,
+                0.03724800109863281,
+                0.03721830368041992,
+                0.0372592658996582,
+                0.03723775863647461,
+                0.037266433715820314,
+                0.0372408332824707,
+                0.03729715347290039,
+                0.0372408332824707,
+                0.037256191253662106,
+                0.03726131057739258,
+                0.0373043212890625,
+                0.03727872085571289,
+                0.03733196640014649,
+                0.03728796768188476,
+                0.03733808135986328,
+                0.03734425735473633,
+                0.037359615325927735,
+                0.03730944061279297,
+                0.037359615325927735,
+                0.03734732818603516,
+                0.037348350524902346,
+                0.03739033508300781,
+                0.037369857788085936,
+                0.0373493766784668,
+                0.03739340972900391,
+                0.037354496002197264,
+                0.03743539047241211,
+                0.03738828659057617,
+                0.03745792007446289,
+                0.0374128646850586,
+                0.03748659133911133,
+                0.037416961669921874,
+                0.03746099090576172,
+                0.03741900634765625,
+                0.0375551986694336,
+                0.03743436813354492,
+                0.03751833724975586,
+                0.03741900634765625,
+                0.03759820938110352,
+                0.03745280075073242,
+                0.037533695220947266,
+                0.037473281860351565,
+                0.03760332870483398,
+                0.03745792007446289,
+                0.037564414978027344,
+                0.03747635269165039,
+                0.03764019012451172,
+                0.03746303939819336,
+                0.037585918426513674,
+                0.037473281860351565,
+                0.037601280212402347,
+                0.03751935958862305,
+                0.03759206390380859,
+                0.037515262603759765,
+                0.03765657424926758,
+                0.03748454284667969,
+                0.0375838737487793,
+                0.03751424026489258,
+                0.03754598236083984,
+                0.037533695220947266,
+                0.037553150177001955,
+                0.03751628875732422,
+                0.03757363128662109,
+                0.037531646728515625,
+                0.0376545295715332,
+                0.03754905700683594,
+                0.03762278366088867,
+                0.037548030853271484,
+                0.03759718322753906,
+                0.03759308624267578,
+                0.03759308624267578,
+                0.0375551986694336,
+                0.037678081512451174,
+                0.03755929565429687,
+                0.03769139099121094,
+                0.03758796691894531,
+                0.037634048461914066,
+                0.03760537719726562,
+                0.03765555191040039,
+                0.037615615844726565,
+                0.037713920593261716,
+                0.037615615844726565,
+                0.03764121627807617,
+                0.037618686676025394,
+                0.03712819290161133,
+                0.037184513092041016,
+                0.037168128967285156,
+                0.03717529678344727,
+                0.037190654754638675,
+                0.03719270324707031,
+                0.03712921524047851,
+                0.037146625518798826,
+                0.03721420669555664,
+                0.03722547149658203,
+                0.037207038879394534,
+                0.03724697494506836,
+                0.03724288177490234,
+                0.03741900634765625,
+                0.0372305908203125,
+                0.03721830368041992,
+                0.03726438522338867,
+                0.03726131057739258,
+                0.037272575378417966,
+                0.037233665466308595,
+                0.03724288177490234,
+                0.03729919815063477,
+                0.03725721740722656,
+                0.03727872085571289,
+                0.03727360153198242,
+                0.03733913421630859,
+                0.03727667236328125,
+                0.03733196640014649,
+                0.03734527969360352,
+                0.03731763076782227,
+                0.0373309440612793,
+                0.03734220886230469,
+                0.037321727752685545,
+                0.03733708953857422,
+                0.03733606338500976,
+                0.037341182708740234,
+                0.03734220886230469,
+                0.03740979385375977,
+                0.037375999450683595,
+                0.03741388702392578,
+                0.03736678314208984,
+                0.037416961669921874,
+                0.03741900634765625,
+                0.03743641662597656,
+                0.037408767700195314,
+                0.037515262603759765,
+                0.037400577545166014,
+                0.03750502395629883,
+                0.03745075225830078,
+                0.03757670211791992,
+                0.03744153594970703,
+                0.037558273315429686,
+                0.03747123336791992,
+                0.03767603302001953,
+                0.03747225570678711,
+                0.037566463470458986,
+                0.03747840118408203,
+                0.03760332870483398,
+                0.03748556900024414,
+                0.03758796691894531,
+                0.03748659133911133,
+                0.03763302230834961,
+                0.03746201705932617,
+                0.03757363128662109,
+                0.037466110229492186,
+                0.037615615844726565,
+                0.0375654411315918,
+                0.03760947036743164,
+                0.0374835205078125,
+                0.03766988754272461,
+                0.0375203857421875,
+                0.0376258544921875,
+                0.037541889190673826,
+                0.03754393768310547,
+                0.037556224822998044,
+                0.03755417633056641,
+                0.037582847595214845,
+                0.037579776763916016,
+                0.037572608947753904,
+                0.03763814544677734,
+                0.03756851196289063,
+                0.03764633560180664,
+                0.037539840698242184,
+                0.03759206390380859,
+                0.03758796691894531,
+                0.03760639953613281,
+                0.037580799102783204,
+                0.03772108840942383,
+                0.037618686676025394,
+                0.03765248107910156,
+                0.037599231719970705,
+                0.03763916778564453,
+                0.03759513473510742,
+                0.0376627197265625,
+                0.03762073516845703,
+                0.037700607299804685,
+                0.0376258544921875,
+                0.03765760040283203,
+                0.037648384094238284
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.42481298105823
+        },
+        "energy": null,
+        "efficiency": null
+    }
+}