The story so far
Weights, every dated article, and repo commits on one rail.
30 repo commits since the weights landed
Teal is the weights (2022-12-02), grey ticks are repo commits.
santacoder
bigcode BigCode OpenRAIL-M out 4 years ago
Text in, text out, 2K tokens of context.
Verified 2026-10-25 Rank #707 in LLMs · score 72 method v1 Sources 3 Downloads 30d 5k · #544 of 619 tracked
Do people use it?5kdownloads, 30 days#544 of 619 we track · below the median+0 likes, downloads −19% this week337 likesHugging Face2026-10-24
Where it's used
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: 100 Spaces.
- As a service0no API provider listed
- On own hardware0quantized builds
- Built on1815 fine-tunes · 3 adapters · 0 merges
- In apps100+Hugging Face Spaces
Top Spaces running it: bigcode/santacoder-demo ♥ 170 · monra/freegpt-webui ♥ 64 · justest/gpt4free ♥ 28 · Yeyito/llm_contamination_detector ♥ 27
What people built on it
18 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
18 derivatives on the Hub, most of them fine-tunes
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Reference
Everything else, folded: the full tables, every source.
Use-case evidence
2 use cases
What it is good at 2 use cases
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.
Facts
19 fields
Listed in LLMs
Facts
- Context length is 2,048 tokens (2K). (config.json max_position_embeddings, observed 2026-10-24)
- License: BigCode OpenRAIL-M (friction: attribution). (license file, observed 2026-10-24)
- Created 2022-12-02, last modified 2023-10-12. (HF API, observed 2026-10-24)
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | GPT2LMHeadCustomModel |
| Model type | gpt2 |
| Dtype | float32 |
| MoE | no |
| Context length | 2,048 (config.json max_position_embeddings) |
| Languages | code |
| Papers | arXiv:1911.02150, arXiv:2207.14255, arXiv:2301.03988 |
| License | BigCode OpenRAIL-M (bigcode-openrail-m) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: not in registry · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · GPT2LMHeadCustomModel · 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.
All variants
18 variants
Lineage
finetune: 15adapter: 3
Top variants (18 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| muhtasham/santacoder-finetuned-the-stack-cobol | finetune | — | — | — | openrail | muhtasham | 6 | 1.6k |
| Vipitis/santacoder-finetuned-Shadertoys-fine | finetune | — | 1.23B | S | bigcode-openrail-m | Vipitis | 0 | 1.7k |
| Vipitis/santacoder-finetuned-the-stack-glsl | finetune | — | 1.23B | S | bigcode-openrail-m | Vipitis | 2 | 1k |
| Vipitis/santacoder-finetuned-Shadertoys | finetune | — | 1.23B | S | bigcode-openrail-m | Vipitis | 2 | 718 |
| aiswaryasankar/santacoder-finetuned-the-stack-bash | finetune | — | — | — | bigcode-openrail-m | aiswaryasankar | 0 | 737 |
| AdnanRiaz107/SCoder-APPS | finetune | — | 1.23B | S | bigcode-openrail-m | AdnanRiaz107 | 1 | 409 |
| GabSo/santacoder-finetuned-the-stack-bash | finetune | — | — | — | bigcode-openrail-m | GabSo | 0 | 368 |
| GabSo/santacoder-finetuned-robot2 | finetune | — | — | — | bigcode-openrail-m | GabSo | 0 | 340 |
| GabSo/santacoder-finetuned-robot4 | finetune | — | 1.23B | S | bigcode-openrail-m | GabSo | 0 | 335 |
| GabSo/santacoder-finetuned-robot | finetune | — | — | — | bigcode-openrail-m | GabSo | 0 | 323 |
| GabSo/santacoder-finetuned-robot3 | finetune | — | 1.23B | S | bigcode-openrail-m | GabSo | 0 | 318 |
| flyover19/santacoder-finetuned-the-stack-bash | finetune | — | — | — | bigcode-openrail-m | flyover19 | 0 | 316 |
| flyover19/10032023 | finetune | — | — | — | bigcode-openrail-m | flyover19 | 0 | 307 |
| iamsajalmondal/santacoder-finetuned-the-stack-bash | finetune | — | 1.23B | S | bigcode-openrail-m | iamsajalmondal | 0 | 105 |
| SalihDundar/lora_fine_tune_600 | adapter | — | — | — | — | SalihDundar | 0 | 70 |
| SalihDundar/lora_fine_tune_500 | adapter | — | — | — | — | SalihDundar | 0 | 34 |
| alexalvarez1/db-trainer-cores | adapter | — | — | — | — | alexalvarez1 | 0 | 20 |
| AdnanRiaz107/SantacoderPEFTLORA-MBPP | finetune | — | — | — | bigcode-openrail-m | AdnanRiaz107 | 0 | 0 |
Repository changelog
30 commits
Repository changelog 30 commits
| Date | Commit | SHA |
|---|---|---|
| 2023-10-12 | add note on fim tokens (#42) | bb3be59 |
| 2023-05-12 | Update README.md | 132eb6b |
| 2023-05-11 | Update README.md | a663ea3 |
| 2023-05-08 | Updated Context length precision | c9442e6 |
| 2023-05-08 | Added missing info about context window | 9e0590a |
| 2023-04-23 | Update eos_token_id / bos_token_id in config.json (#19) | 0b048f3 |
| 2023-04-03 | Activate inference API (#26) | 6a4fb77 |
| 2023-03-22 | Fix link (#24) | bb63c0e |
| 2023-02-20 | Fix char typo in README (#20) | e464072 |
| 2023-02-02 | Fix typo (#16) | 636ad0a |
| 2023-01-27 | Switch from PreTrainedTokenizerFast to GPT2TokenizerFast and add eos_token & bos_token (#15) | 47ad9f0 |
| 2023-01-25 | Update tokenizer (#11) | cd86b97 |
| 2023-01-17 | update paper link to arxiv | 3482bf4 |
| 2023-01-17 | Update README with citation (#12) | bb6706d |
| 2023-01-06 | Add max length to tokenizer | aaeed52 |
| 2022-12-23 | Update README.md | cfee4c0 |
| 2022-12-23 | Update configuration_gpt2_mq.py (#6) | 79d9bea |
| 2022-12-23 | add link to the paper (#7) | 959bf80 |
| 2022-12-22 | link to space (#5) | baec3a0 |
| 2022-12-22 | Fix model device in code example (#4) | 3d4d383 |
| 2022-12-22 | Update README.md | d3c3868 |
| 2022-12-22 | Update README.md | e02c7b7 |
| 2022-12-22 | Update README.md | 718da24 |
| 2022-12-22 | Update README.md | bdeb6cc |
| 2022-12-22 | Update model card Attribution Section (#3) | fa6c997 |
| 2022-12-22 | Update README.md | bf8ac45 |
| 2022-12-22 | Merge branch 'dedup-alt-comments' | 26708d1 |
| 2022-12-21 | Update README.md | 417a7b1 |
| 2022-12-21 | Update README.md | 600be72 |
| 2022-12-21 | Update README.md | f6b437c |
Papers
3 papers
Papers 3
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).
- SantaCoder: don't reach for the stars! this model
Similar models
3 models
Similar models
- opt-125m same task (text-generation)
- gpt-j-6b same task (text-generation), permissive license
- DialoGPT-medium same task (text-generation), permissive license
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:42 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:13 UTC · Last verified 2026-10-25
Follow santacoder
Watch this model
- /feeds/models/bigcode--santacoder.xml(RSS 2.0) · every change to santacoder
- /feeds/families/bigcode--santacoder.xml(RSS 2.0) · every change across the santacoder family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.