Up to date
facebook Other out 4 years ago
Text in, text out, 2K tokens of context.
Verified 2026-10-25 Rank #133 in LLMs · score 94.3 method v1 Sources 3 Downloads 30d 5.4M · #28 of 619 tracked
Changed this week: 1 new quantized build on the Hub (14 in all).2026-10-24
Picked by rule from 7 tracked pieces: the lab's own post, the most shared, a field report, the latest.
GPT-2 and OPT-125M share a skeleton of 12 layers and 768 dimensions but exhibit radically different internal dynamics during inference.
The 2 picks above, plus these 5. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
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.
No API provider serves it, so its downloads are people running it themselves: 14 quantized builds and 100 Spaces.
Top Spaces running it: badayvedat/LLaVA ♥ 425 · LanguageBind/Video-LLaVA ♥ 234 · embedl/hfviewer ♥ 181 · THUdyh/Oryx ♥ 102
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2022-05-11), amber triangles are 2 dated articles (each links to it), grey ticks are repo commits.
435 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.
OPT-125m is a decoder-only pre-trained transformer model designed for text generation.[1]
Generated 2026-10-07 15:02 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
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 LLMs
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | OPTForCausalLM |
| Model type | opt |
| Dtype | float16 |
| MoE | no |
| Context length | 2,048 (config.json max_position_embeddings) |
| Languages | en |
| Papers | arXiv:2205.01068, arXiv:2005.14165 |
| License | Other (other) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · OPTForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · OPTForCausalLM · 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.
adapter: 321finetune: 100quantized: 14
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| peft-internal-testing/opt-125m-dummy-lora | adapter | — | — | — | — | peft-internal-testing | 0 | 139.2k |
| pszemraj/opt-125m-email-generation | finetune | — | 125M | S | other | pszemraj | 3 | 9.7k |
| jwongTensora/test-repo | finetune | — | 125M | S | other | jwongTensora | 0 | 2k |
| Xenova/opt-125m | quantized | — | — | — | — | Xenova | 0 | 1.4k |
| nicholasKluge/Aira-OPT-125M | finetune | — | 125M | S | other | nicholasKluge | 0 | 1.2k |
| ryota-komatsu/SylReg-LM-85M | finetune | — | 132M | S | — | ryota-komatsu | 0 | 1k |
| Cheng98/opt-125m-sst2 | finetune | — | — | — | other | Cheng98 | 0 | 934 |
| mendeza/opt-125m-synthetic-finetuned | finetune | — | 125M | S | other | mendeza | 0 | 769 |
| Herocat/opt-125m-finetuned-wikitext2 | finetune | — | 125M | S | other | Herocat | 0 | 747 |
| SystemAdmin123/opt-125m | finetune | — | 125M | S | other | SystemAdmin123 | 0 | 737 |
| SirSahOl/opt-125m-chat-mlx-16bit | finetune | mlx | 164M | S | other | SirSahOl | 0 | 641 |
| ansilmbabl/ft-opt-125m-customer-chatbot-4-zephyr-tokenizer | finetune | — | 125M | S | other | ansilmbabl | 1 | 556 |
| krushnakant27/bertQA | finetune | — | 125M | S | other | krushnakant27 | 0 | 570 |
| jeanlucmarsh/opt-125m-pattern-based_finetuning_with_lora-mnli-mm-d3_fs2 | adapter | — | — | — | other | jeanlucmarsh | 0 | 536 |
| Cheng98/opt-125m-qnli | finetune | — | — | — | other | Cheng98 | 0 | 513 |
| ybelkada/test-axolotl-onecyclelrschedulertrainer | finetune | — | 125M | S | other | ybelkada | 0 | 495 |
| Cheng98/opt-125m-rte | finetune | — | — | — | other | Cheng98 | 0 | 491 |
| ybelkada/test-axolotl-axolotlmambatrainer | finetune | — | 125M | S | other | ybelkada | 0 | 488 |
| ybelkada/test-axolotl | finetune | — | 125M | S | other | ybelkada | 0 | 462 |
| ellen625/opt125_wiki_rlo_k50 | finetune | — | 125M | S | other | ellen625 | 0 | 460 |
| Cheng98/opt-125m-qqp | finetune | — | — | — | other | Cheng98 | 0 | 459 |
| ellen625/opt125_wiki_ce | finetune | — | 125M | S | other | ellen625 | 0 | 451 |
| kashif/gkd_openassistant-guanaco | finetune | — | 125M | S | other | kashif | 0 | 445 |
| tomaszki/mail_fixer | finetune | — | — | — | other | tomaszki | 0 | 431 |
| SebastianSchramm/opt-125m-sft-full | finetune | — | 125M | S | other | SebastianSchramm | 0 | 426 |
| ellen625/opt125_wiki_rlo_k3 | finetune | — | 125M | S | other | ellen625 | 0 | 426 |
| ellen625/opt_125_wiki_k10 | finetune | — | 125M | S | other | ellen625 | 0 | 421 |
| monsterapi/opt125M_alpaca | adapter | — | — | — | — | monsterapi | 0 | 416 |
| ellen625/ft_opt125_ce | finetune | — | 125M | S | other | ellen625 | 0 | 412 |
| gnumanth/tmp_trainer | finetune | — | 125M | S | other | gnumanth | 0 | 411 |
| ansilmbabl/ft-opt-125m-customer-chatbot-3 | finetune | — | 125M | S | other | ansilmbabl | 0 | 405 |
| ansilmbabl/ft-opt-125m-customer-chatbot-2 | finetune | — | 125M | S | other | ansilmbabl | 0 | 381 |
| error577/5f0159c4-1008-4527-9092-4ee6e6b9e663 | adapter | — | — | — | other | error577 | 0 | 333 |
| VisitationAI/opt125-llama-visitation | finetune | — | 125M | S | llama3 | VisitationAI | 0 | 309 |
| AlexKoff88/opt-125m-openvino-4bit | finetune | -4bit | — | — | other | AlexKoff88 | 0 | 285 |
| quansuv/opt-125m-finetuned-wikitext-103 | finetune | — | 125M | S | other | quansuv | 0 | 262 |
| elliottfitzgerald/opt-125m-finetuned-mnli-mm | adapter | — | 125M | S | other | elliottfitzgerald | 0 | 217 |
| SirSahOl/opt-125m-chat-mlx-4bit | quantized | mlx | 164M | S | other | SirSahOl | 0 | 216 |
| mahojo/opt-125m-cluster-v2 | finetune | — | 125M | S | other | mahojo | 0 | 171 |
| Albatu1773/opt-125m-fine-tuned-lora-model | adapter | — | — | — | — | Albatu1773 | 1 | 112 |
| Date | Commit | SHA |
|---|---|---|
| 2023-09-15 | Update README.md (#38) | 27dcfa7 |
| 2023-01-24 | Adding generation config file(s) | 3d2b5f2 |
| 2022-06-22 | Update README.md (#5) | 934b6a0 |
| 2022-06-21 | correct checkpoints see: https://github.com/facebookresearch/metaseq/pull/164 | 507a399 |
| 2022-06-16 | Update TF weights (#2) | 38f3ba0 |
| 2022-06-03 | Add flax_weights | 80cabbb |
| 2022-06-03 | Add tf_weights | c681a93 |
| 2022-06-03 | Update README.md | 449ab1c |
| 2022-06-03 | add model | 6fb0883 |
| 2022-05-26 | Change BOS token from 0 to 2 as BOS token is equal to EOS for OPT. See: https://github.com/huggingface/transformers/issues/17431 (#1) | da93426 |
| 2022-05-25 | Update tokenizer_config.json | 1c370c8 |
| 2022-05-25 | Upload tf_model.h5 | 46941ec |
| 2022-05-24 | Update tf weights | 75f3881 |
| 2022-05-19 | Update tf weights | 71aed4d |
| 2022-05-18 | Upload tf_model.h5 | 13ec9fc |
| 2022-05-18 | Update config.json | c1c6d4a |
| 2022-05-17 | add model | fae5403 |
| 2022-05-16 | Set commercial attribute to False | 403005f |
| 2022-05-16 | Update license | 5c42793 |
| 2022-05-16 | Update licence | 83a28f5 |
| 2022-05-13 | Temporarily deactivate the inference API | 2affb45 |
| 2022-05-13 | Update config.json | 74b53f9 |
| 2022-05-12 | Update README.md | 0770005 |
| 2022-05-12 | Update README.md | 853beb2 |
| 2022-05-12 | Create README.md | 97c3f46 |
| 2022-05-12 | finish | 04e12f0 |
| 2022-05-12 | finish | fde505d |
| 2022-05-12 | Merge branch 'main' of https://huggingface.co/facebook/opt-125m into main | 141c875 |
| 2022-05-12 | add tokenizer | c29996b |
| 2022-05-12 | Update config.json | 3bbf6e4 |
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 15:02 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.
