AwAppp
/

benchmark_original_batch_size25

Transformers

Model card Files Files and versions

xet

Community

AwAppp commited on Mar 6, 2024

Commit

c383314

verified ·

1 Parent(s): 26b0227

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": 1476.096,
+            "max_vram": 15674.114048,
+            "max_reserved": 15189.671936,
+            "max_allocated": 15039.57248
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 0.04060129179605625,
+            "stdev": 9.672596162009366e-05,
+            "values": [
+                0.041347713470458985,
+                0.04112588882446289,
+                0.041048000335693356,
+                0.04107161712646484,
+                0.04105420684814453,
+                0.041047039031982424,
+                0.0409354248046875,
+                0.04108697509765625,
+                0.04071731185913086,
+                0.04058313751220703,
+                0.040600574493408204,
+                0.04060876846313476,
+                0.04061183929443359,
+                0.04065280151367188,
+                0.04060774230957031,
+                0.04060467147827149,
+                0.04065788650512695,
+                0.040602622985839845,
+                0.040671230316162106,
+                0.04064255905151367,
+                0.040586238861083986,
+                0.04059340667724609,
+                0.040615936279296876,
+                0.04061491012573242,
+                0.040619007110595705,
+                0.040574977874755856,
+                0.04060979080200195,
+                0.040622081756591794,
+                0.04063334274291992,
+                0.040600574493408204,
+                0.04058009719848633,
+                0.04061183929443359,
+                0.04056979370117188,
+                0.04060467147827149,
+                0.040637439727783206,
+                0.04064761734008789,
+                0.04058214569091797,
+                0.04057292938232422,
+                0.04061183929443359,
+                0.04064665603637695,
+                0.04059545516967773,
+                0.040635391235351564,
+                0.04059648132324219,
+                0.04058726501464844,
+                0.04059033584594727,
+                0.040561664581298826,
+                0.04064972686767578,
+                0.04053606414794922,
+                0.040583168029785156,
+                0.04058214569091797,
+                0.04063334274291992,
+                0.040594432830810545,
+                0.04059648132324219,
+                0.04056268692016601,
+                0.04055859375,
+                0.040561664581298826,
+                0.04059033584594727,
+                0.04055859375,
+                0.040591358184814456,
+                0.0405032958984375,
+                0.040574977874755856,
+                0.04058214569091797,
+                0.04057088088989258,
+                0.040578048706054685,
+                0.04059743881225586,
+                0.04061798477172852,
+                0.04056576156616211,
+                0.04056063842773437,
+                0.040583168029785156,
+                0.040613887786865234,
+                0.0406036491394043,
+                0.04060361480712891,
+                0.04062822341918945,
+                0.04056576156616211,
+                0.04060876846313476,
+                0.040627201080322264,
+                0.04058009719848633,
+                0.04056371307373047,
+                0.04057395172119141,
+                0.04058009719848633,
+                0.04057702255249023,
+                0.04061695861816406,
+                0.04060569763183594,
+                0.04060671997070313,
+                0.04057696151733398,
+                0.0405852165222168,
+                0.040613887786865234,
+                0.04061798477172852,
+                0.040574977874755856,
+                0.04056979370117188,
+                0.04062003326416016,
+                0.04057286453247071,
+                0.040592384338378903,
+                0.040567806243896484,
+                0.040583168029785156,
+                0.04058726501464844,
+                0.040576000213623044,
+                0.040613887786865234,
+                0.040597503662109374,
+                0.04057907104492187,
+                0.040545280456542966,
+                0.04060460662841797,
+                0.04062003326416016,
+                0.040602622985839845,
+                0.04060774230957031,
+                0.040581119537353515,
+                0.040574977874755856,
+                0.04057907104492187,
+                0.040653823852539066,
+                0.040610816955566405,
+                0.04060160064697266,
+                0.04058828735351563,
+                0.040542209625244144,
+                0.04058726501464844,
+                0.040548351287841795,
+                0.040610816955566405,
+                0.04054937744140625,
+                0.04057702255249023,
+                0.040591358184814456,
+                0.04059648132324219,
+                0.040581119537353515,
+                0.040622081756591794,
+                0.04060876846313476,
+                0.040548351287841795,
+                0.040576000213623044,
+                0.04056268692016601,
+                0.040574977874755856,
+                0.0405667839050293,
+                0.040599552154541016,
+                0.040569854736328126,
+                0.04058726501464844,
+                0.04056268692016601,
+                0.040592384338378903,
+                0.04055859375,
+                0.040581119537353515,
+                0.040561664581298826,
+                0.04055756759643555,
+                0.040574977874755856,
+                0.04058009719848633,
+                0.040610816955566405,
+                0.040548351287841795,
+                0.04053807830810547,
+                0.04056063842773437,
+                0.040586238861083986,
+                0.04063334274291992,
+                0.04060774230957031,
+                0.04062515258789062,
+                0.0406036491394043,
+                0.040632320404052735,
+                0.040597503662109374,
+                0.04059545516967773,
+                0.040600574493408204,
+                0.040584190368652344,
+                0.04053094482421875,
+                0.040612865447998046,
+                0.04055654525756836,
+                0.04058931350708008,
+                0.04054937744140625,
+                0.040567806243896484,
+                0.04057292938232422,
+                0.04058214569091797,
+                0.04057702255249023,
+                0.04064153671264648,
+                0.0406036491394043,
+                0.04054732894897461,
+                0.040581119537353515,
+                0.04058009719848633,
+                0.04056883239746094,
+                0.04060876846313476,
+                0.04058214569091797,
+                0.04057596969604492,
+                0.0405667839050293,
+                0.040610816955566405,
+                0.04056576156616211,
+                0.04053504180908203,
+                0.04054118347167969,
+                0.04053401565551758,
+                0.04052377700805664,
+                0.040548351287841795,
+                0.04057395172119141,
+                0.04058931350708008,
+                0.04057702255249023,
+                0.04056576156616211,
+                0.04055756759643555,
+                0.04057187271118164,
+                0.04055859375,
+                0.040548351287841795,
+                0.040574977874755856,
+                0.04052070236206055,
+                0.04059545516967773,
+                0.040569854736328126,
+                0.04055449676513672,
+                0.04060979080200195,
+                0.04057702255249023,
+                0.040528896331787106,
+                0.04055244827270508,
+                0.04055756759643555,
+                0.04058009719848633,
+                0.040619007110595705,
+                0.040645633697509766,
+                0.040621055603027346,
+                0.04058726501464844,
+                0.040600574493408204,
+                0.04055039978027344,
+                0.04062822341918945,
+                0.04060467147827149,
+                0.040599552154541016,
+                0.040548351287841795,
+                0.040569854736328126,
+                0.04057292938232422,
+                0.040610816955566405,
+                0.040564735412597655,
+                0.04056371307373047,
+                0.04055756759643555,
+                0.04058828735351563,
+                0.040583168029785156,
+                0.04059033584594727,
+                0.04053913497924805,
+                0.04057292938232422,
+                0.040564735412597655,
+                0.04054732894897461,
+                0.040583168029785156,
+                0.04061491012573242,
+                0.04053094482421875,
+                0.04053811264038086,
+                0.04057395172119141,
+                0.0405667839050293,
+                0.04052275085449219,
+                0.04059033584594727,
+                0.04058828735351563,
+                0.04058009719848633,
+                0.04058726501464844,
+                0.04062412643432617,
+                0.040621055603027346,
+                0.040602622985839845,
+                0.040564735412597655,
+                0.04057088088989258,
+                0.04057190322875977,
+                0.040586238861083986,
+                0.0405401611328125,
+                0.040497150421142575,
+                0.04051251220703125,
+                0.040525825500488284,
+                0.04055756759643555,
+                0.040529918670654294,
+                0.04052787017822266
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 788.1522627589961
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "decode": {
+        "memory": {
+            "unit": "MB",
+            "max_ram": 1487.01184,
+            "max_vram": 15739.12576,
+            "max_reserved": 15254.683648,
+            "max_allocated": 15101.761024
+        },
+        "latency": {
+            "unit": "s",
+            "mean": 3.7079623514811195,
+            "stdev": 0.0005176731659298959,
+            "values": [
+                3.7086382026672364,
+                3.707380710601807,
+                3.707868141174314
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.39860042562468
+        },
+        "energy": null,
+        "efficiency": null
+    },
+    "per_token": {
+        "memory": null,
+        "latency": {
+            "unit": "s",
+            "mean": 0.037454165166475956,
+            "stdev": 0.00015713925002910255,
+            "values": [
+                0.037207038879394534,
+                0.037171199798583986,
+                0.03721113586425781,
+                0.037184513092041016,
+                0.03719372940063476,
+                0.03722547149658203,
+                0.03721625518798828,
+                0.03726028823852539,
+                0.03726028823852539,
+                0.03727974319458008,
+                0.037266433715820314,
+                0.0372674560546875,
+                0.037272575378417966,
+                0.03726335906982422,
+                0.03728793716430664,
+                0.037275646209716795,
+                0.03726028823852539,
+                0.03727667236328125,
+                0.03729817581176758,
+                0.03728793716430664,
+                0.03729612731933594,
+                0.03729817581176758,
+                0.037256191253662106,
+                0.03727667236328125,
+                0.03727155303955078,
+                0.037303295135498044,
+                0.03732889556884766,
+                0.03736883163452148,
+                0.037285888671875,
+                0.03735859298706055,
+                0.03734425735473633,
+                0.03736883163452148,
+                0.03738009643554688,
+                0.03736883163452148,
+                0.03738214492797851,
+                0.03736064147949219,
+                0.03738828659057617,
+                0.03740467071533203,
+                0.03735756683349609,
+                0.03747020721435547,
+                0.03737497711181641,
+                0.03745075225830078,
+                0.037395454406738284,
+                0.03743743896484375,
+                0.03741183853149414,
+                0.037459968566894535,
+                0.03744768142700195,
+                0.03748863983154297,
+                0.03743948745727539,
+                0.037591041564941405,
+                0.037482494354248046,
+                0.037566463470458986,
+                0.03745280075073242,
+                0.03761356735229492,
+                0.03747635269165039,
+                0.03759820938110352,
+                0.03749990463256836,
+                0.03762176132202148,
+                0.037495807647705076,
+                0.037577728271484374,
+                0.0374917106628418,
+                0.03764121627807617,
+                0.037512191772460936,
+                0.03765350341796875,
+                0.037498878479003905,
+                0.03764019012451172,
+                0.037525505065917966,
+                0.037645313262939455,
+                0.03755929565429687,
+                0.037664768218994144,
+                0.03758694458007812,
+                0.037601280212402347,
+                0.03751935958862305,
+                0.037585918426513674,
+                0.037574657440185545,
+                0.03760025787353516,
+                0.0376627197265625,
+                0.03759001541137695,
+                0.03761459350585938,
+                0.03762790298461914,
+                0.03757875061035156,
+                0.03762688064575195,
+                0.03760639953613281,
+                0.037631999969482424,
+                0.03759718322753906,
+                0.03768320083618164,
+                0.0375838737487793,
+                0.03773952102661133,
+                0.03763507080078125,
+                0.037644287109375,
+                0.03763507080078125,
+                0.03765862274169922,
+                0.03762790298461914,
+                0.037651454925537106,
+                0.037634048461914066,
+                0.037751808166503906,
+                0.03758694458007812,
+                0.037634048461914066,
+                0.03761663818359375,
+                0.037198848724365234,
+                0.037157886505126955,
+                0.03719270324707031,
+                0.03721011352539062,
+                0.03719475173950195,
+                0.037190654754638675,
+                0.03719987106323242,
+                0.03719680023193359,
+                0.03722649765014648,
+                0.037275646209716795,
+                0.0372408332824707,
+                0.0372408332824707,
+                0.037217281341552735,
+                0.03724800109863281,
+                0.03722547149658203,
+                0.03725721740722656,
+                0.03727462387084961,
+                0.037294078826904296,
+                0.03725721740722656,
+                0.03729612731933594,
+                0.03724492645263672,
+                0.03732889556884766,
+                0.03727769470214844,
+                0.03726847839355469,
+                0.0372674560546875,
+                0.03735039901733399,
+                0.037275646209716795,
+                0.0373196792602539,
+                0.03731763076782227,
+                0.03733401489257813,
+                0.03729817581176758,
+                0.0373831672668457,
+                0.03732992172241211,
+                0.037348350524902346,
+                0.03733913421630859,
+                0.03738828659057617,
+                0.0373831672668457,
+                0.03742310333251953,
+                0.037395454406738284,
+                0.03742822265625,
+                0.037378047943115236,
+                0.03745280075073242,
+                0.037395454406738284,
+                0.03749273681640625,
+                0.03740979385375977,
+                0.03750912094116211,
+                0.03745382308959961,
+                0.03747840118408203,
+                0.03743641662597656,
+                0.037591041564941405,
+                0.03747225570678711,
+                0.03755724716186523,
+                0.03743334579467773,
+                0.037572608947753904,
+                0.03746099090576172,
+                0.037531646728515625,
+                0.037473281860351565,
+                0.03763711929321289,
+                0.03746815872192383,
+                0.03759513473510742,
+                0.03747532653808594,
+                0.03768012619018555,
+                0.03750604629516602,
+                0.037548030853271484,
+                0.03751833724975586,
+                0.037599231719970705,
+                0.03750400161743164,
+                0.03767295837402344,
+                0.03750092697143555,
+                0.03769241714477539,
+                0.0375470085144043,
+                0.0376360969543457,
+                0.037531646728515625,
+                0.0375623664855957,
+                0.037564414978027344,
+                0.03756851196289063,
+                0.037553150177001955,
+                0.03760332870483398,
+                0.03755724716186523,
+                0.03762688064575195,
+                0.03754393768310547,
+                0.03760025787353516,
+                0.037599231719970705,
+                0.03757363128662109,
+                0.037579776763916016,
+                0.03762073516845703,
+                0.03762073516845703,
+                0.037719039916992186,
+                0.037550079345703126,
+                0.037610496520996094,
+                0.037585918426513674,
+                0.03763916778564453,
+                0.03762176132202148,
+                0.03763711929321289,
+                0.03764223861694336,
+                0.03772927856445313,
+                0.03763097763061524,
+                0.037689342498779296,
+                0.03764223861694336,
+                0.03719782257080078,
+                0.03715584182739258,
+                0.03719168090820312,
+                0.03718048095703125,
+                0.03720185470581055,
+                0.03721625518798828,
+                0.03715584182739258,
+                0.037182464599609374,
+                0.03722956848144531,
+                0.037256191253662106,
+                0.03722649765014648,
+                0.0372592658996582,
+                0.03724492645263672,
+                0.03726438522338867,
+                0.03723980712890625,
+                0.03723980712890625,
+                0.03723571014404297,
+                0.03725823974609375,
+                0.037275646209716795,
+                0.03728179168701172,
+                0.03723980712890625,
+                0.03727974319458008,
+                0.03729817581176758,
+                0.03731455993652344,
+                0.037285888671875,
+                0.03731148910522461,
+                0.03729919815063477,
+                0.037341182708740234,
+                0.03736883163452148,
+                0.03735244750976562,
+                0.03736064147949219,
+                0.03737395095825195,
+                0.03735244750976562,
+                0.037362686157226564,
+                0.037362686157226564,
+                0.037362686157226564,
+                0.037367809295654295,
+                0.03738214492797851,
+                0.03739340972900391,
+                0.03741593551635742,
+                0.03740262222290039,
+                0.03747123336791992,
+                0.03744768142700195,
+                0.03744153594970703,
+                0.03745382308959961,
+                0.03747532653808594,
+                0.037465087890625,
+                0.03748863983154297,
+                0.037454849243164064,
+                0.03761971282958984,
+                0.037498878479003905,
+                0.037564414978027344,
+                0.03745280075073242,
+                0.03765760040283203,
+                0.03746713638305664,
+                0.037577728271484374,
+                0.03750092697143555,
+                0.037628929138183595,
+                0.03750604629516602,
+                0.037591041564941405,
+                0.037515262603759765,
+                0.03763097763061524,
+                0.03746815872192383,
+                0.037553150177001955,
+                0.0374917106628418,
+                0.037617664337158206,
+                0.03752959823608398,
+                0.03759513473510742,
+                0.0375470085144043,
+                0.03768012619018555,
+                0.03750707244873047,
+                0.0376258544921875,
+                0.03753062438964844,
+                0.03762176132202148,
+                0.03758489608764649,
+                0.03758182525634766,
+                0.03755929565429687,
+                0.03757567977905273,
+                0.03755724716186523,
+                0.03763916778564453,
+                0.03754086303710937,
+                0.03762073516845703,
+                0.03757567977905273,
+                0.037602302551269534,
+                0.037602302551269534,
+                0.03763814544677734,
+                0.03760332870483398,
+                0.03771084976196289,
+                0.03762688064575195,
+                0.037634048461914066,
+                0.03759718322753906,
+                0.03765862274169922,
+                0.03762790298461914,
+                0.0376627197265625,
+                0.03763711929321289,
+                0.03772313690185547,
+                0.03762073516845703,
+                0.03763302230834961,
+                0.0376545295715332
+            ]
+        },
+        "throughput": {
+            "unit": "tokens/s",
+            "value": 53.39860042562468
+        },
+        "energy": null,
+        "efficiency": null
+    }
+}