Up to date
facebook Apache 2.0 out 5 years ago
139M parameters, text in, embeddings out, 1K tokens of context. 1 provider serves it.
Verified 2026-10-25 Rank #40 in Embeddings · score 91.8 method v1 Sources 3 Downloads 30d 235.5k · #237 of 619 tracked
Picked by rule from 2 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 1 pick above, plus these 1. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
| # | Cheapest live row | In /1M | Out /1M | Context | Quant | Seen |
|---|---|---|---|---|---|---|
| 1 | HF Inference | — | — | — | — | Oct 25 |
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Served by 1 API provider; 1 quantized build for local use; a big base for builders (587 fine-tunes, adapters and merges).
Top Spaces running it: gunship999/SexyImages ♥ 439 · hilamanor/audioEditing ♥ 330 · Audio-AGI/AudioSep ♥ 222 · jadechoghari/OpenMusic ♥ 212
Weights only, an estimate: leave room for the KV cache. Method
About 0.1 GB at INT4, 0.2 GB at FP8, 0.3 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2022-03-02), amber triangles are 1 dated article (each links to it), grey ticks are repo commits.
588 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
Listed in Embeddings
| Pipeline tag | feature-extraction |
|---|---|
| Library | transformers |
| Architectures | BartModel |
| Model type | bart |
| Dtype | float32 |
| Params by dtype | F32: 139,420,416 |
| Size band | S |
| MoE | no |
| Context length | 1,024 (config.json max_position_embeddings) |
| Languages | en |
| Papers | arXiv:1910.13461 |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
vLLM: not in registry · BartModel · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: not in registry · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for bart-base: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.3 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 0.2 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.1 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
finetune: 523adapter: 64quantized: 1
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| avisena/bart-base-job-info-summarizer | finetune | — | 139M | S | unknown | avisena | 4 | 43.3k |
| scbirlab/lchemme-base-zinc22-lteq300 | finetune | — | 101M | S | mit | scbirlab | 0 | 41k |
| s-nlp/bart-base-detox | finetune | — | 139M | S | openrail++ | s-nlp | 12 | 27.3k |
| VidhuMathur/bart-log-summarization | finetune | — | — | — | mit | VidhuMathur | 5 | 10.1k |
| GuysTrans/bart-base-finetuned-xsum | finetune | — | 139M | S | apache-2.0 | GuysTrans | 0 | 9.8k |
| morenolq/bart-base-xsum | finetune | — | 139M | S | apache-2.0 | morenolq | 2 | 5.5k |
| rrrr66254/Glossa-BART | finetune | — | 139M | S | — | rrrr66254 | 1 | 5.2k |
| Ssarion/bart-base-multi-news | finetune | — | 139M | S | apache-2.0 | Ssarion | 0 | 3.7k |
| GuysTrans/bart-base-mini | finetune | — | — | — | apache-2.0 | GuysTrans | 1 | 3k |
| razhan/bart-kurd-spell-base | finetune | — | 139M | S | apache-2.0 | razhan | 5 | 2.5k |
| sjrhuschlee/bart-base-squad2 | finetune | — | 139M | S | mit | sjrhuschlee | 0 | 1.7k |
| Someman/bart-hindi | finetune | — | 139M | S | apache-2.0 | Someman | 1 | 1.2k |
| pijarcandra22/NMTIndoBaliBART | finetune | — | — | — | apache-2.0 | pijarcandra22 | 0 | 1.3k |
| cive202/humanize-ai-text-bart-base | finetune | — | 139M | S | mit | cive202 | 0 | 1.3k |
| raeidsaqur/bart-base | finetune | — | 139M | S | apache-2.0 | raeidsaqur | 0 | 1.2k |
| GuysTrans/bart-base-vn-re-attention-vn-tokenizer | finetune | — | 139M | S | apache-2.0 | GuysTrans | 0 | 953 |
| eilamc14/bart-base-text-simplification | finetune | — | 139M | S | apache-2.0 | eilamc14 | 0 | 953 |
| zbigi/bart-base-lora-summarization-medical | adapter | — | — | — | apache-2.0 | zbigi | 1 | 867 |
| diya2022/bart-text-summarizer | finetune | — | 139M | S | apache-2.0 | diya2022 | 1 | 861 |
| santiviquez/bart-base-finetuned-samsum-en | finetune | — | — | — | apache-2.0 | santiviquez | 0 | 910 |
| Pavan48/bart-base-cnn-dailymail-highlights-128 | finetune | — | 139M | S | mit | Pavan48 | 0 | 773 |
| rohitsroch/hybrid_hbh_bart-base_icsi_sum | finetune | — | 139M | S | apache-2.0 | rohitsroch | 0 | 718 |
| dtruong46me/train-bart-base | finetune | — | 139M | S | mit | dtruong46me | 1 | 655 |
| elvisbakunzi/dyslexia-friendly-text-simplifier | finetune | — | 139M | S | apache-2.0 | elvisbakunzi | 0 | 704 |
| rohitsroch/hybrid_utt-clusterrank_bart-base_samsum_sum | finetune | — | 139M | S | apache-2.0 | rohitsroch | 0 | 688 |
| eliolio/bart-finetuned-yelpreviews | finetune | — | 139M | S | apache-2.0 | eliolio | 0 | 672 |
| pszemraj/bart-base-code-instructiongen | finetune | — | 139M | S | apache-2.0cc-by-nc-4.0 | pszemraj | 0 | 632 |
| 425GMM/bart-base-aslg-gloss | finetune | — | 139M | S | apache-2.0 | 425GMM | 0 | 631 |
| yoeel/bart-cnn-summarizer | finetune | — | 139M | S | apache-2.0 | yoeel | 0 | 623 |
| CyrexPro/bart-base-finetuned-cnn_dailymail | finetune | — | 139M | S | apache-2.0 | CyrexPro | 0 | 583 |
| razhan/bart-kurd-spell-base-05 | finetune | — | — | — | apache-2.0 | razhan | 0 | 543 |
| Hawoly16/SN_chatbot | finetune | — | 139M | S | apache-2.0 | Hawoly16 | 0 | 529 |
| xshubhamx/bart-base | finetune | — | 140M | S | apache-2.0 | xshubhamx | 0 | 500 |
| scbirlab/lchemme-base-dosedo-lteq300 | finetune | — | 101M | S | mit | scbirlab | 0 | 491 |
| GuysTrans/bart-base-re-attention-mini-seq-512 | finetune | — | 139M | S | apache-2.0 | GuysTrans | 0 | 487 |
| Vexemous/bart-base-finetuned-xsum | finetune | — | 139M | S | apache-2.0 | Vexemous | 0 | 475 |
| Binaryy/bart-base-finetuned-findsum | finetune | — | 139M | S | apache-2.0 | Binaryy | 0 | 458 |
| razhan/bart-kurd-spell-base-05_10 | finetune | — | 139M | S | apache-2.0 | razhan | 0 | 457 |
| rooftopcoder/tst-summarization | finetune | — | — | — | apache-2.0 | rooftopcoder | 0 | 452 |
| onionLad/grammar-correction-bart-base | finetune | — | 139M | S | apache-2.0 | onionLad | 0 | 443 |
| Date | Commit | SHA |
|---|---|---|
| 2022-11-16 | Adding `safetensors` variant of this model (#2) | aadd2ab |
| 2022-06-03 | typo: encoder-encoder -> encoder-decoder (#1) | 8435883 |
| 2022-03-09 | Update config.json | d0af988 |
| 2021-10-01 | remove ipynb file | ea0107e |
| 2021-10-01 | update mask token embeddings | b0c3779 |
| 2021-09-16 | Fix code example | 7652e0c |
| 2021-09-16 | Add model card | 51f9983 |
| 2021-06-14 | add flax model | c5eee23 |
| 2021-03-09 | Move tokenizer.json from roberta-large | c2469fb |
| 2020-11-24 | Added vocabulary files from robert-large repo | df1e90c |
| 2020-10-26 | Update config.json | b2ec1a3 |
| 2020-10-15 | Update tf_model.h5 | fc8b0d2 |
| 2020-10-05 | Update config.json | 2557745 |
| 2020-08-17 | Update config.json | d7db7a7 |
| 2020-06-15 | Update config.json | bc16ad0 |
| 2020-06-15 | Update pytorch_model.bin | 757bac0 |
| 2020-06-15 | Update config.json | a0f3da1 |
| 2020-06-15 | Update config.json | e658f90 |
| 2020-06-15 | initial commit | a1f138e |
Hosted endpoints observed for bart-base, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| HF Inference hf | facebook/bart-base | — | — | — | — | — | — | — | live | 2026-10-25 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:35 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:03 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.
