Template:Infobox model: Difference between revisions
Appearance
New infobox for AI models, with benchmarks |
Pass banner and logo through |
||
| Line 1: | Line 1: | ||
<includeonly>{{Infobox | <includeonly>{{Infobox | ||
| title = {{{title|{{{name|{{PAGENAME}}}}}}}} | | title = {{{title|{{{name|{{PAGENAME}}}}}}}} | ||
| banner = {{{banner|}}} | |||
| banner_size = {{{banner_size|400px}}} | |||
| banner_caption = {{{banner_caption|}}} | |||
| banner_alt = {{{banner_alt|}}} | |||
| logo = {{{logo|}}} | |||
| logo_size = {{{logo_size|120px}}} | |||
| logo_caption = {{{logo_caption|}}} | |||
| logo_alt = {{{logo_alt|}}} | |||
| image = {{{image|}}} | | image = {{{image|}}} | ||
| image_size = {{{image_size|220px}}} | | image_size = {{{image_size|220px}}} | ||
| Line 72: | Line 80: | ||
{{Infobox model | {{Infobox model | ||
| title = Example-1 | | title = Example-1 | ||
| logo = Gorilla-Computer-Desktop.svg | |||
| logo_size = 72px | |||
| logo_caption = Icon by Jakub Steiner, [https://creativecommons.org/licenses/by-sa/2.0/ CC BY-SA 2.0] | |||
| developer = Example Lab | | developer = Example Lab | ||
| family = Example | | family = Example | ||
| Line 109: | Line 120: | ||
{{Infobox model | {{Infobox model | ||
| title = <!-- defaults to the page name --> | | title = <!-- defaults to the page name --> | ||
| image = <!-- | | banner = <!-- wide image across the top, above the title --> | ||
| banner_size = <!-- defaults to 400px (shrinks to fit) --> | |||
| banner_caption = | |||
| logo = <!-- logo under the title --> | |||
| logo_size = <!-- defaults to 120px --> | |||
| logo_caption = | |||
| image = <!-- e.g. a sample output or diagram; file name without "File:" --> | |||
| image_size = | | image_size = | ||
| caption = | | caption = | ||
| Line 165: | Line 182: | ||
}} | }} | ||
</pre> | </pre> | ||
* <code>banner</code> runs across the top of the box, above the title; <code>logo</code> sits under the title. Both are optional and work alongside <code>image</code>. | |||
* Benchmark scores are percentages; write them as <code>61.2</code> or <code>61.2%</code>. Each gets a small bar. | * Benchmark scores are percentages; write them as <code>61.2</code> or <code>61.2%</code>. Each gets a small bar. | ||
* A score that isn't a percentage, such as <code>18.7 ppl</code>, is shown as written, without a bar, and left out of the mean. | * A score that isn't a percentage, such as <code>18.7 ppl</code>, is shown as written, without a bar, and left out of the mean. | ||
Revision as of 00:11, 16 November 2026
Example-1
Overview
Developer
Example Lab
Family
Example
Type
Base (pretrained)
License
Apache 2.0
Status
Released
Architecture
Architecture
Decoder-only transformer
Parameters
125M
Layers
12
Context length
2,048 tokens
Tokenizer
32k BPE
Training
Tokens
50B
Tokens / param
400 Chinchilla-optimal ≈ 20
Data
FineWeb-Edu
Hardware
1 × example GPU
Training time
9 days
Precision
fp16 mixed
Benchmarks
HellaSwag zero-shot
33.1
ARC-Easy zero-shot
48.0
PIQA zero-shot
64.5
Example-Bench
18.7 ppl
Mean 3 tasks
48.5
acc_norm where available, lm-evaluation-harness
Links
Weights
Formats
safetensors, GGUF
- Released10 months, 7 days ago
Example models
← Preceded by
Example-0Succeeded by →
Example-2An infobox for AI models: language models, image models, anything with weights. It is Template:Infobox with model fields built in, and every field is optional: empty rows and empty sections are hidden. The example above is made up.
Usage
{{Infobox model
| title = <!-- defaults to the page name -->
| banner = <!-- wide image across the top, above the title -->
| banner_size = <!-- defaults to 400px (shrinks to fit) -->
| banner_caption =
| logo = <!-- logo under the title -->
| logo_size = <!-- defaults to 120px -->
| logo_caption =
| image = <!-- e.g. a sample output or diagram; file name without "File:" -->
| image_size =
| caption =
<!-- Overview -->
| developer = <!-- e.g. [[OpenCerebral]] -->
| family = <!-- e.g. Boris -->
| model_type = <!-- Base, Instruct, Chat, Reasoning ... -->
| base_model = <!-- shown as "Fine-tuned from" -->
| license =
| status = <!-- Training, Released, Preview, Retired ... -->
<!-- Architecture -->
| architecture = <!-- e.g. Decoder-only transformer, MHA, RoPE -->
| parameters = <!-- 125M, 1.5B ... -->
| layers =
| context = <!-- context length -->
| tokenizer = <!-- e.g. 32k BPE -->
<!-- Training -->
| training_tokens = <!-- 31B, 1.2 trillion ... -->
| tokens_per_param = <!-- worked out from parameters and training_tokens if left empty -->
| dataset =
| hardware =
| training_time =
| compute = <!-- GPU-hours or FLOPs -->
| precision = <!-- fp16 mixed, bf16 ... -->
<!-- Benchmarks: score, optional _shots, _ref (a comparison score) and _mean = no -->
| hellaswag = | hellaswag_shots = | hellaswag_ref =
| arc_easy = | arc_challenge =
| piqa = | winogrande = | openbookqa =
| boolq = | sciq = | lambada =
| mmlu = | gsm8k = | humaneval =
| bench1 = | bench1_score = <!-- any other benchmark, up to bench30 -->
| bench1_shots = | bench1_ref =
| bench_ref_label = <!-- column heading for the _ref scores, e.g. GPT-2 XL -->
| bench_mean = <!-- "no" hides the mean row -->
| bench_note = <!-- metric and harness, e.g. acc_norm, lm-evaluation-harness -->
| bench_source = <!-- link to where the numbers come from -->
<!-- Links -->
| weights = <!-- e.g. [https://huggingface.co/... Hugging Face] -->
| formats = <!-- safetensors, GGUF ... -->
| demo =
| paper =
| code =
| website =
<!-- History timeline: same events as Template:Infobox -->
| released = <!-- release date; 2026, 2026-10 or 2026-10-21 -->
| renamed = | renamed_to =
| event1_date = | event1 = <!-- e.g. weights updated -->
| dissolved = <!-- date it was retired -->
| show_age = <!-- "no" hides the "... ago" pills -->
<!-- Chronology -->
| series = <!-- e.g. Boris models -->
| preceded_by =
| succeeded_by =
<!-- extra rows: header26-30, label26-30, data26-30; footer: below -->
}}
bannerruns across the top of the box, above the title;logosits under the title. Both are optional and work alongsideimage.- Benchmark scores are percentages; write them as
61.2or61.2%. Each gets a small bar. - A score that isn't a percentage, such as
18.7 ppl, is shown as written, without a bar, and left out of the mean. - With two or more percentage scores, a Mean row is added. Leave a task out of it with
hellaswag_mean = no(orbench1_mean = no), or hide the row withbench_mean = no. - Give
_refscores (for example a well-known model of the same size) and a Ref. column appears. Name it withbench_ref_label. The reference mean is shown only when every task in the mean has a reference score. _shots = 0shows zero-shot;5shows 5-shot.- Tokens / param is worked out from
parametersandtraining_tokenswhen both are numbers like125Mand50B. releasedadds a dated row with how long ago it was. Renames, retirements and other events turn it into a timeline, as in Template:Infobox.- Articles using this box are added to Category:Models.