Up to date
openai-community MIT out 5 years ago
120M parameters, text in, text out, 512 tokens of context.
Verified 2026-10-25 Rank #758 in LLMs · score 71.3 method v1 Sources 3 Downloads 30d 99k · #316 of 619 tracked
Picked by rule from 20 tracked pieces: the lab's own post, the most shared, a field report, the latest.
GPT–6 Astra broke the German Army Enigma message MVUEH from 10 July 1941, which had resisted all attempts since 2005.
The 2 picks above, plus these 18. 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: 89 Spaces.
Top Spaces running it: yizhangliu/Grounded-Segment-Anything ♥ 395 · banana-projects/transformer-autocomplete ♥ 24 · ethanchern/Anole ♥ 21 · sonalkum/GAMA ♥ 17
Weights only, an estimate: leave room for the KV cache. Method
About 0.1 GB at INT4, 0.1 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 10 dated articles (each links to it), grey ticks are repo commits.
13 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.
OpenAI GPT is a 120M parameter transformer-based language model designed for text generation.[1][2] The model is a causal transformer pre-trained for English language modeling tasks.[3]
Generated 2026-10-07 15:12 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 | OpenAIGPTLMHeadModel |
| Model type | openai-gpt |
| Params by dtype | F32: 119,680,512 |
| Size band | S |
| MoE | no |
| Context length | 512 (config.json max_position_embeddings) |
| Languages | en |
| Papers | arXiv:1705.11168, arXiv:1803.02324, arXiv:1910.09700 |
| License | MIT (mit) |
| Hub snapshot | 2026-10-25 |
vLLM: not in registry · 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 openai-gpt: 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) | 0.1 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: 13
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| vietnhatthai/test_pretrain_pipeline | finetune | — | — | — | mit | vietnhatthai | 0 | 429 |
| tmnam20/test_pretrain_pipeline | finetune | — | — | — | mit | tmnam20 | 0 | 376 |
| vietnhatthai/viet_news_pretrain_pipeline | finetune | — | — | — | mit | vietnhatthai | 0 | 346 |
| Dave12121/chatFsentiment | finetune | — | — | — | mit | Dave12121 | 0 | 244 |
| jacob-danner/gpt_1_sequence_classification_finetune | finetune | — | 117M | S | mit | jacob-danner | 0 | 234 |
| goktug14/gpt1_sst2_right | finetune | — | 117M | S | mit | goktug14 | 0 | 149 |
| goktug14/gpt1_sst2_left | finetune | — | 117M | S | mit | goktug14 | 0 | 112 |
| jacob-danner/gpt_1_causual_finetune | finetune | — | 117M | S | mit | jacob-danner | 0 | 97 |
| zeromodels/gpt | finetune | — | — | — | mit | zeromodels | 0 | 73 |
| iscii/market-sentiment-learn | finetune | — | — | — | — | iscii | 0 | 0 |
| Murfi75/WinrixAI | finetune | — | — | — | apache-2.0 | Murfi75 | 0 | 0 |
| Benlehn/productmanagerhiringtrainer | finetune | — | — | — | apache-2.0 | Benlehn | 0 | 0 |
| Hanish/sparse-steer-gpt1 | finetune | — | — | — | mit | Hanish | 0 | 0 |
| Date | Commit | SHA |
|---|---|---|
| 2024-02-19 | Adds the tokenizer configuration file (#6) | 1e0d4f3 |
| 2024-01-19 | historical note? (#5) | 61cf0c7 |
| 2023-04-06 | Adding `safetensors` variant of this model (#3) | adacbec |
| 2023-01-24 | Adding generation config file(s) | 173722e |
| 2022-07-22 | Add model card (#1) | b3ab194 |
| 2020-12-09 | For clarity, delete deprecated modelcard.json | f5d4376 |
| 2020-10-12 | Update tokenizer.json | 1fb4b04 |
| 2020-05-11 | Update config.json | 8f7daab |
| 2020-04-24 | Update rust_model.ot | 47d5381 |
| 2020-04-24 | Update config.json | ea7c5d8 |
| 2020-01-31 | Update config.json | 3a007b9 |
| 2019-12-20 | Update modelcard.json | 11c4ddd |
| 2019-09-24 | Update tf_model.h5 | 6de569c |
| 2019-02-08 | Update config.json | 6a659dc |
| 2019-02-08 | Update config.json | e4cabe4 |
| 2019-02-06 | Update merges.txt | 75b1daa |
| 2019-02-06 | Update pytorch_model.bin | 3aa6e29 |
| 2019-02-06 | Update vocab.json | 2060b44 |
| 2019-01-08 | Update vocab.json | 93abf4e |
| 2019-01-08 | Update merges.txt | 93e4e9b |
| 2019-01-08 | initial commit | 3539c00 |
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 21:40 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:12 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.
