The story so far
Weights, every dated article, and repo commits on one rail.
20 repo commits since the weights landed
Teal is the weights (2022-03-02), grey ticks are repo commits.
Models › DialoGPT-small family
DialoGPT-small
176M parameters, text in, text out, 1K tokens of context.
Verified 2026-10-25 Rank #457 in LLMs · score 77.8 method v1 Sources 3 Downloads 30d 46.3k · #390 of 619 tracked
Do people use it?46.3kdownloads, 30 days#390 of 619 we track · below the median+2 likes, downloads +6% this week154 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: 18 quantized builds and 100 Spaces.
- As a service0no API provider listed
- On own hardware18quantized builds
- Built on8354 fine-tunes · 21 adapters · 8 merges
- In apps100+Hugging Face Spaces
Top Spaces running it: yerang/LivePortrait2 ♥ 4 · vasu0508/Meena_Chatbot ♥ 3 · baouws/codel ♥ 3 · rivapereira123/firstaid ♥ 3
Will it fit?
Weights only, an estimate: leave room for the KV cache. Method
Fits a 16 GB card at INT4
About 0.1 GB at INT4, 0.2 GB at FP8, 0.4 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
What people built on it
101 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
101 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.
Benchmarks
8 rows
Benchmarks 8 rows
measured third-party leaderboard rowauthor-reported number from the model card or eval files (8)No confidence intervals unless the source gave them; settings differ between rows, so compare within a benchmark, not across. Date = the benchmark's own date when it gives one, else when we read it.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported ARC (25-shot) | 25.77 | — | model author | 2026-10-07 |
| author-reported Avg. | 25.02 | — | model author | 2026-10-07 |
| author-reported DROP (3-shot) | 0 | — | model author | 2026-10-07 |
| author-reported GSM8K · Reason through hard problems | 0 | — | model author | 2026-10-07 |
| author-reported HellaSwag · Chat and follow instructions | 25.79 | — | model author | 2026-10-07 |
| author-reported MMLU · Reason through hard problems | 25.81 | — | model author | 2026-10-07 |
| author-reported TruthfulQA · Chat and follow instructions | 47.49 | — | model author | 2026-10-07 |
| author-reported Winogrande · Chat and follow instructions | 50.28 | — | model author | 2026-10-07 |
What the card says
1 cited sentence
Use-case evidence
3 use cases
What it is good at 3 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.
- Chat and follow instructionsauthor-reportedAuthor reports HellaSwag (10-shot) 25.79Author reports TruthfulQA (0-shot) 47.49Author reports Winogrande (5-shot) 50.28+2 more
- Reason through hard problemsauthor-reportedAuthor reports MMLU (5-shot) 25.81Author reports GSM8K (5-shot) 0.0
- Run on a laptop or phonestructuraldecision-model estimate p=0.94name: smallfits: edge
Facts
19 fields
Listed in LLMs
Facts
- DialoGPT-small has 176M parameters. (safetensors metadata, observed 2026-10-24)
- Context length is 1,024 tokens (1K). (config.json max_position_embeddings, observed 2026-10-24)
- License: MIT (friction: none). Permissive. (license file, observed 2026-10-24)
- Created 2022-03-02, last modified 2024-02-29. (HF API, observed 2026-10-24)
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | GPT2LMHeadModel |
| Model type | gpt2 |
| Params by dtype | F16: 175,620,096 |
| Size band | S |
| MoE | no |
| Context length | 1,024 (config.json max_position_embeddings) |
| Papers | arXiv:1911.00536 |
| License | MIT (mit) |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: supported · GPT2LMHeadModel · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · GPT2LMHeadModel · 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.
Hardware fit
3 estimates
Hardware fit ESTIMATE
Weights-only memory for DialoGPT-small: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.4 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.
All variants
40 variants
Lineage
finetune: 54adapter: 21quantized: 18merge: 8
Top variants (40 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| ostorc/Conversational_Spanish_GPT | finetune | — | 124M | S | — | ostorc | 9 | 13.3k |
| iamhariraj/DialoGPT-small-Rick | finetune | — | — | — | mit | iamhariraj | 1 | 7k |
| DedeProGames/dialochess | finetune | — | 124M | S | mit | DedeProGames | 0 | 1.9k |
| SaadHS98/DialoGPT-small-garycoleman | finetune | — | 124M | S | — | SaadHS98 | 1 | 1.5k |
| qazws345/DialogGPT_Psycho8k | finetune | — | 124M | S | mit | qazws345 | 0 | 913 |
| cvnberk/DialoGPT-small-crd3 | finetune | — | — | — | mit | cvnberk | 0 | 493 |
| wyuancs/fine_tuned_DialogueGPT_on_DailyDialog | finetune | — | — | — | mit | wyuancs | 0 | 475 |
| Prezily/gpt2-trial-r2 | finetune | — | 124M | S | mit | Prezily | 0 | 463 |
| sweatSmile/DialoGPT-Financial-Market-Sentiment-Trading-Assistant | adapter | — | 124M | S | mit | sweatSmile | 5 | 206 |
| schnabear/DialoGPT-small-FinalFantasyDialogue | finetune | — | — | — | mit | schnabear | 0 | 449 |
| LuangMV97/DialoGPT_EmpAI_small | finetune | — | 124M | S | mit | LuangMV97 | 0 | 441 |
| Yumeng-Liu/YumengBot | finetune | — | 124M | S | mit | Yumeng-Liu | 1 | 390 |
| thealper2/dialogpt-small-dailydialog | finetune | — | 124M | S | cc-by-nc-sa-4.0 | thealper2 | 0 | 440 |
| LuangMV97/DialoGPT_EmpAI_smallPrueba2 | finetune | — | 124M | S | mit | LuangMV97 | 0 | 396 |
| LuangMV97/DialoGPT_EmpAI_final2 | finetune | — | 124M | S | mit | LuangMV97 | 0 | 370 |
| amayuru5678/sl-domestic-violence-legal-lora | adapter | — | — | — | — | amayuru5678 | 0 | 336 |
| Dagonez/DialoGPT-small-Barney-Bot | finetune | — | 355M | S | — | Dagonez | 0 | 325 |
| anktechsol/ankiGPT-small | finetune | — | 124M | S | mit | anktechsol | 1 | 268 |
| chimchimba/dialogpt-customer-support | finetune | — | 163M | S | mit | chimchimba | 0 | 257 |
| devparagiri/convex-2-20250731-194022 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 233 |
| devparagiri/a-20250817-103351 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 217 |
| sweatSmile/DialoGPT-Financial-Wealth-Management-Advisor | adapter | — | 124M | S | mit | sweatSmile | 1 | 141 |
| afscomercial/streamlit-chatbot-aviation | finetune | — | 124M | S | mit | afscomercial | 1 | 135 |
| devparagiri/acme-20250720-094933 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 175 |
| BuyTee/dialo-techsupport | finetune | — | 124M | S | mit | BuyTee | 0 | 171 |
| amitom/gpt2-DiabloGPT-TA | merge | — | 163M | S | — | amitom | 0 | 168 |
| devparagiri/acme-20250721-025929 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 165 |
| devparagiri/acmes-20250722-092611 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 160 |
| onnx-community/DialoGPT-small-ONNX | quantized | — | — | — | mit | onnx-community | 0 | 151 |
| AbdullahAi2005/cashapp-fresh | finetune | — | 124M | S | mit | AbdullahAi2005 | 0 | 145 |
| devparagiri/acme-20250721-033720 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 143 |
| devparagiri/acmes-20250722-230949 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 140 |
| devparagiri/acme-20250720-053326 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 139 |
| ajsal27/results | adapter | — | — | — | mit | ajsal27 | 1 | 88 |
| devparagiri/acme-20250721-030327 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 131 |
| devparagiri/test-2-20250731-195041 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 129 |
| vpadaraju/misafetychatbot | finetune | — | 124M | S | mit | vpadaraju | 0 | 128 |
| devparagiri/TEST-2-20250728-013552 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 127 |
| devparagiri/acmes-20250722-230042 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 125 |
| devparagiri/test-1-20250728-055006 | quantized | GGUF | 124M | S | other | devparagiri | 0 | 124 |
Repository changelog
20 commits
Repository changelog 20 commits
| Date | Commit | SHA |
|---|---|---|
| 2024-02-29 | Fix Conversational Widget (#9) | 49c5371 |
| 2024-02-16 | Add default chat template to tokenizer_config.json (#8) | abd2854 |
| 2023-11-28 | Adding Evaluation Results (#5) | 14b0073 |
| 2023-06-26 | Adding `safetensors` variant of this model (#2) | 97d0fec |
| 2023-01-24 | Adding generation config file(s) | 4e936e3 |
| 2021-05-23 | upload flax model | f9c829d |
| 2021-05-23 | allow flax | 4d13fd5 |
| 2021-02-23 | Update tokenizer_config.json | 9fb5c2d |
| 2021-02-23 | Create tokenizer_config.json | 364722e |
| 2020-12-11 | Migrate model card from transformers-repo | 2f89b19 |
| 2020-10-14 | Update config.json | ac43d91 |
| 2020-04-24 | Update config.json | b7ac3a6 |
| 2020-04-11 | Update tf_model.h5 | 730b69f |
| 2020-03-23 | Update config.json | 46bd8a3 |
| 2020-03-11 | Update config.json | fe20bc6 |
| 2020-03-10 | Update pytorch_model.bin | fbb567d |
| 2020-03-10 | Update vocab.json | 6af4e59 |
| 2020-03-10 | Update merges.txt | dd81ba1 |
| 2020-03-10 | Update config.json | 84fac20 |
| 2020-03-10 | initial commit | a13386b |
Papers
1 paper
Papers 1
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).
Similar models
3 models
Similar models
- gpt-neo-125m · 150M same size band (S), same task (text-generation), permissive license
- gpt2 · 137M same size band (S), same task (text-generation), permissive license
- pythia-160m · 213M same size band (S), same task (text-generation), permissive license
Sources
3 sources
Sources
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
Follow DialoGPT-small
Watch this model
- /feeds/models/microsoft--DialoGPT-small.xml(RSS 2.0) · every change to DialoGPT-small
- /feeds/families/microsoft--DialoGPT-small.xml(RSS 2.0) · every change across the DialoGPT-small family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.