AwAppp
/

benchmark_original_batch_size15

Transformers

Model card Files Files and versions

xet

Community

AwAppp commited on Mar 6, 2024

Commit

fc97652

verified ·

1 Parent(s): e7adae6

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": 1476.337664,
+            "max_vram": 15674.114048,
+            "max_reserved": 15189.671936,
+            "max_allocated": 15039.57248
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 0.04062422609716893,
+            "stdev": 0.00010050440174907307,
+            "values": [
+                0.041370719909667966,
+                0.04117913436889648,
+                0.04108595275878906,
+                0.04110847854614258,
+                0.041082878112792966,
+                0.04110028839111328,
+                0.041022464752197264,
+                0.04113919830322266,
+                0.04074905776977539,
+                0.04062617492675781,
+                0.04065792083740234,
+                0.040648704528808595,
+                0.040668159484863284,
+                0.040627201080322264,
+                0.040629249572753906,
+                0.04065075302124024,
+                0.04069375991821289,
+                0.04066099166870117,
+                0.04063846588134765,
+                0.040651775360107424,
+                0.04060870361328125,
+                0.04064153671264648,
+                0.040653823852539066,
+                0.04065484619140625,
+                0.04063334274291992,
+                0.04061491012573242,
+                0.040629249572753906,
+                0.04061798477172852,
+                0.040681472778320314,
+                0.040627201080322264,
+                0.04065484619140625,
+                0.04067942428588867,
+                0.0406036491394043,
+                0.04064153671264648,
+                0.04065788650512695,
+                0.04061695861816406,
+                0.040597503662109374,
+                0.04061183929443359,
+                0.040627201080322264,
+                0.040645633697509766,
+                0.04062412643432617,
+                0.04062412643432617,
+                0.04062617492675781,
+                0.040613887786865234,
+                0.040635391235351564,
+                0.04061183929443359,
+                0.04062617492675781,
+                0.040564735412597655,
+                0.040619007110595705,
+                0.04065792083740234,
+                0.04064767837524414,
+                0.04062515258789062,
+                0.04057292938232422,
+                0.040559616088867184,
+                0.040627201080322264,
+                0.04053401565551758,
+                0.04064972686767578,
+                0.04055654525756836,
+                0.04059648132324219,
+                0.040567806243896484,
+                0.04060774230957031,
+                0.04062611389160156,
+                0.040591358184814456,
+                0.04058726501464844,
+                0.040610816955566405,
+                0.040622081756591794,
+                0.040613887786865234,
+                0.040619007110595705,
+                0.04060671997070313,
+                0.04061491012573242,
+                0.04060876846313476,
+                0.04061798477172852,
+                0.04061491012573242,
+                0.04059648132324219,
+                0.040576000213623044,
+                0.04062003326416016,
+                0.04057395172119141,
+                0.0405852165222168,
+                0.04058828735351563,
+                0.040583168029785156,
+                0.04059340667724609,
+                0.04058931350708008,
+                0.040612865447998046,
+                0.040629249572753906,
+                0.04064051055908203,
+                0.0406343994140625,
+                0.04064972686767578,
+                0.04062412643432617,
+                0.040583168029785156,
+                0.040615936279296876,
+                0.040671230316162106,
+                0.040548351287841795,
+                0.040559616088867184,
+                0.040599552154541016,
+                0.04060563278198242,
+                0.04063436889648438,
+                0.04060160064697266,
+                0.040635391235351564,
+                0.040551422119140625,
+                0.040597503662109374,
+                0.040613887786865234,
+                0.04060876846313476,
+                0.040632320404052735,
+                0.04060467147827149,
+                0.04059852981567383,
+                0.040600574493408204,
+                0.040583168029785156,
+                0.04057395172119141,
+                0.040615936279296876,
+                0.04060876846313476,
+                0.04060774230957031,
+                0.04062412643432617,
+                0.040629249572753906,
+                0.04064767837524414,
+                0.04055244827270508,
+                0.04061894226074219,
+                0.040576000213623044,
+                0.040591358184814456,
+                0.04063948822021484,
+                0.04060774230957031,
+                0.040594432830810545,
+                0.04063641738891602,
+                0.040653823852539066,
+                0.04062617492675781,
+                0.040635391235351564,
+                0.04056268692016601,
+                0.040586238861083986,
+                0.04057190322875977,
+                0.040584190368652344,
+                0.04058723068237305,
+                0.04060569763183594,
+                0.04057395172119141,
+                0.04059545516967773,
+                0.040635391235351564,
+                0.040597503662109374,
+                0.040621055603027346,
+                0.040630271911621094,
+                0.04061798477172852,
+                0.04058828735351563,
+                0.040612865447998046,
+                0.040584190368652344,
+                0.040635391235351564,
+                0.0405852165222168,
+                0.04060876846313476,
+                0.040619007110595705,
+                0.04064255905151367,
+                0.040632320404052735,
+                0.04064153671264648,
+                0.04064051055908203,
+                0.040578048706054685,
+                0.040594432830810545,
+                0.04056883239746094,
+                0.040643585205078124,
+                0.0405667839050293,
+                0.04060979080200195,
+                0.040584190368652344,
+                0.04061491012573242,
+                0.04060671997070313,
+                0.040600574493408204,
+                0.040578048706054685,
+                0.04060671997070313,
+                0.040583168029785156,
+                0.040637439727783206,
+                0.040578048706054685,
+                0.04061798477172852,
+                0.040602622985839845,
+                0.040610782623291014,
+                0.04059952163696289,
+                0.040592384338378903,
+                0.04060774230957031,
+                0.04062003326416016,
+                0.040567806243896484,
+                0.0406036491394043,
+                0.04057907104492187,
+                0.040567806243896484,
+                0.0406036491394043,
+                0.04056371307373047,
+                0.0405667839050293,
+                0.040602622985839845,
+                0.040586238861083986,
+                0.04061177444458008,
+                0.040613887786865234,
+                0.040568801879882814,
+                0.040610816955566405,
+                0.040602622985839845,
+                0.04057088088989258,
+                0.04059033584594727,
+                0.040583168029785156,
+                0.04054937744140625,
+                0.04060774230957031,
+                0.04056883239746094,
+                0.04057088088989258,
+                0.040592384338378903,
+                0.040594432830810545,
+                0.040551422119140625,
+                0.04057190322875977,
+                0.04055654525756836,
+                0.04062617492675781,
+                0.04064972686767578,
+                0.04064665603637695,
+                0.04064150238037109,
+                0.04059648132324219,
+                0.040594432830810545,
+                0.0406640625,
+                0.040653823852539066,
+                0.040627201080322264,
+                0.04060870361328125,
+                0.04061695861816406,
+                0.04055756759643555,
+                0.040621055603027346,
+                0.04062822341918945,
+                0.04059648132324219,
+                0.04058828735351563,
+                0.04060467147827149,
+                0.04060774230957031,
+                0.04058726501464844,
+                0.04056063842773437,
+                0.04058009719848633,
+                0.040594432830810545,
+                0.04061183929443359,
+                0.04059648132324219,
+                0.04060160064697266,
+                0.04054323196411133,
+                0.040559616088867184,
+                0.04061183929443359,
+                0.04057702255249023,
+                0.040602622985839845,
+                0.040569854736328126,
+                0.0405555534362793,
+                0.040564735412597655,
+                0.040564735412597655,
+                0.04058931350708008,
+                0.040681472778320314,
+                0.04062003326416016,
+                0.04063641738891602,
+                0.0406036491394043,
+                0.04060876846313476,
+                0.0405852165222168,
+                0.04061798477172852,
+                0.04055756759643555,
+                0.04053708648681641,
+                0.04055654525756836,
+                0.04055654525756836,
+                0.04058009719848633,
+                0.04057088088989258,
+                0.04057190322875977
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 787.7073134503368
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "decode": {
+        "memory": {
+            "unit": "MB",
+            "max_ram": 1487.241216,
+            "max_vram": 15739.12576,
+            "max_reserved": 15254.683648,
+            "max_allocated": 15101.761024
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 3.709987153371175,
+            "stdev": 0.0002519454973644119,
+            "values": [
+                3.710313472747803,
+                3.7097000923156727,
+                3.7099478950500484
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.369457039785765
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "per_token": {
+        "memory": null,
+        "latency": {
+            "unit": "s",
+            "mean": 0.03747461771081997,
+            "stdev": 0.00015825306347794503,
+            "values": [
+                0.03728179168701172,
+                0.03722751998901367,
+                0.037203968048095705,
+                0.03723263931274414,
+                0.037195777893066405,
+                0.037198848724365234,
+                0.03725516891479492,
+                0.037233665466308595,
+                0.03720908737182617,
+                0.0372592658996582,
+                0.03727872085571289,
+                0.03729919815063477,
+                0.037236736297607424,
+                0.03731763076782227,
+                0.03727769470214844,
+                0.03727155303955078,
+                0.03726847839355469,
+                0.037266433715820314,
+                0.03724390411376953,
+                0.037362686157226564,
+                0.03730124664306641,
+                0.03729715347290039,
+                0.03727462387084961,
+                0.037324798583984374,
+                0.03729817581176758,
+                0.03739033508300781,
+                0.03735551834106445,
+                0.037384193420410154,
+                0.03735859298706055,
+                0.0373493766784668,
+                0.037364734649658206,
+                0.037440513610839846,
+                0.037354496002197264,
+                0.037381118774414065,
+                0.03738726425170898,
+                0.03740671920776367,
+                0.03738623809814453,
+                0.03744255828857422,
+                0.037369857788085936,
+                0.03748454284667969,
+                0.03745382308959961,
+                0.03746303939819336,
+                0.03743436813354492,
+                0.03750400161743164,
+                0.03746406555175781,
+                0.03748556900024414,
+                0.037495807647705076,
+                0.03753676986694336,
+                0.03748659133911133,
+                0.037591041564941405,
+                0.037498878479003905,
+                0.03759206390380859,
+                0.037465087890625,
+                0.03761971282958984,
+                0.03746201705932617,
+                0.037582847595214845,
+                0.03748556900024414,
+                0.037628929138183595,
+                0.03750297546386719,
+                0.03762790298461914,
+                0.03750809478759766,
+                0.0376995849609375,
+                0.03750092697143555,
+                0.03761356735229492,
+                0.03753062438964844,
+                0.03764633560180664,
+                0.03759513473510742,
+                0.037694465637207034,
+                0.03756032180786133,
+                0.03770675277709961,
+                0.037577728271484374,
+                0.0376627197265625,
+                0.037599231719970705,
+                0.037615615844726565,
+                0.0375470085144043,
+                0.03758899307250976,
+                0.037594112396240234,
+                0.037602302551269534,
+                0.03753881454467774,
+                0.03767295837402344,
+                0.0375551986694336,
+                0.037612545013427735,
+                0.037566463470458986,
+                0.0376258544921875,
+                0.03760435104370117,
+                0.03763097763061524,
+                0.03767091369628906,
+                0.03770470428466797,
+                0.03762688064575195,
+                0.03768627166748047,
+                0.03762790298461914,
+                0.037667839050292966,
+                0.03764121627807617,
+                0.037718017578125,
+                0.037634048461914066,
+                0.037789695739746096,
+                0.03763507080078125,
+                0.03768115234375,
+                0.03772518539428711,
+                0.03724595260620117,
+                0.03719168090820312,
+                0.03719782257080078,
+                0.037250049591064455,
+                0.03724595260620117,
+                0.037215232849121094,
+                0.03723980712890625,
+                0.03723571014404297,
+                0.037207038879394534,
+                0.03724492645263672,
+                0.03724595260620117,
+                0.037256191253662106,
+                0.037222400665283206,
+                0.03728384017944336,
+                0.037266433715820314,
+                0.037238784790039066,
+                0.037253120422363284,
+                0.03729305648803711,
+                0.03723468780517578,
+                0.037285888671875,
+                0.03728691101074219,
+                0.03729715347290039,
+                0.03729817581176758,
+                0.03728998565673828,
+                0.037302272796630856,
+                0.0373309440612793,
+                0.0373309440612793,
+                0.037354496002197264,
+                0.03732992172241211,
+                0.03735039901733399,
+                0.037362686157226564,
+                0.0374466552734375,
+                0.037379070281982424,
+                0.03735551834106445,
+                0.03737190246582031,
+                0.03739955139160156,
+                0.03741183853149414,
+                0.037405696868896485,
+                0.037384193420410154,
+                0.03742822265625,
+                0.03746406555175781,
+                0.03746406555175781,
+                0.037438465118408204,
+                0.037501953125,
+                0.03742924880981445,
+                0.03750297546386719,
+                0.03746099090576172,
+                0.03754393768310547,
+                0.03746918487548828,
+                0.0375838737487793,
+                0.037482494354248046,
+                0.03760748672485351,
+                0.03745785522460938,
+                0.03763814544677734,
+                0.03750809478759766,
+                0.03757875061035156,
+                0.0374917106628418,
+                0.037628929138183595,
+                0.037531646728515625,
+                0.03763814544677734,
+                0.03754393768310547,
+                0.03769651031494141,
+                0.037531646728515625,
+                0.037618686676025394,
+                0.03753881454467774,
+                0.03763302230834961,
+                0.037564414978027344,
+                0.03763916778564453,
+                0.03751833724975586,
+                0.03770265579223633,
+                0.037528575897216795,
+                0.03770880126953125,
+                0.037564414978027344,
+                0.03760639953613281,
+                0.03759308624267578,
+                0.03759718322753906,
+                0.03762278366088867,
+                0.03757363128662109,
+                0.03761971282958984,
+                0.03766067123413086,
+                0.03758182525634766,
+                0.037631999969482424,
+                0.037594112396240234,
+                0.03762176132202148,
+                0.037585918426513674,
+                0.0376258544921875,
+                0.03765248107910156,
+                0.03772518539428711,
+                0.037594112396240234,
+                0.03762790298461914,
+                0.037615615844726565,
+                0.03770880126953125,
+                0.03761151885986328,
+                0.03765043258666992,
+                0.03762790298461914,
+                0.03776409530639648,
+                0.0376545295715332,
+                0.03766886520385742,
+                0.03770163345336914,
+                0.03721420669555664,
+                0.03719987106323242,
+                0.03718963241577149,
+                0.03722649765014648,
+                0.03723468780517578,
+                0.037212158203125,
+                0.03723571014404297,
+                0.03726028823852539,
+                0.037236736297607424,
+                0.03727462387084961,
+                0.03724185562133789,
+                0.03727667236328125,
+                0.03724800109863281,
+                0.03731353759765625,
+                0.03729817581176758,
+                0.037288959503173826,
+                0.03726028823852539,
+                0.03731660842895508,
+                0.03725823974609375,
+                0.03728998565673828,
+                0.03728486251831055,
+                0.0373043212890625,
+                0.03728691101074219,
+                0.03732582473754883,
+                0.037269504547119144,
+                0.03735551834106445,
+                0.03734527969360352,
+                0.037351425170898435,
+                0.037354496002197264,
+                0.03737497711181641,
+                0.037318656921386716,
+                0.037395454406738284,
+                0.037389312744140625,
+                0.03735756683349609,
+                0.03741798400878906,
+                0.03743436813354492,
+                0.03741183853149414,
+                0.037424129486083986,
+                0.03739136123657227,
+                0.03742822265625,
+                0.03745280075073242,
+                0.03746815872192383,
+                0.03739340972900391,
+                0.03748147201538086,
+                0.03744672012329102,
+                0.037521343231201175,
+                0.03745894241333008,
+                0.03750604629516602,
+                0.03746099090576172,
+                0.03760025787353516,
+                0.037459968566894535,
+                0.03759308624267578,
+                0.03749273681640625,
+                0.03766579055786133,
+                0.0374917106628418,
+                0.037566463470458986,
+                0.037533695220947266,
+                0.03763916778564453,
+                0.03750604629516602,
+                0.03763097763061524,
+                0.037477375030517575,
+                0.03767097473144531,
+                0.03749881744384766,
+                0.037599231719970705,
+                0.037571582794189456,
+                0.03767603302001953,
+                0.037582847595214845,
+                0.03766067123413086,
+                0.03754086303710937,
+                0.037705726623535156,
+                0.0375551986694336,
+                0.037644287109375,
+                0.037577728271484374,
+                0.037596160888671876,
+                0.037569534301757815,
+                0.0375838737487793,
+                0.037574657440185545,
+                0.03758899307250976,
+                0.03759823989868164,
+                0.03772003173828125,
+                0.037563392639160156,
+                0.03759820938110352,
+                0.037558273315429686,
+                0.037571582794189456,
+                0.0376258544921875,
+                0.037647361755371096,
+                0.03762995147705078,
+                0.0376995849609375,
+                0.03763097763061524,
+                0.03766886520385742,
+                0.03762278366088867,
+                0.03768115234375,
+                0.03763814544677734,
+                0.037684223175048825,
+                0.03766579055786133,
+                0.03776204681396484,
+                0.03766067123413086,
+                0.03769343948364258,
+                0.037684223175048825
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.369457039785736
+        },
+        "energy": null,
+        "efficiency": null
+    }
+}