Field report
llm-explorer.com
The story so far
Weights, every dated article, and repo commits on one rail.
18 repo commits since the weights landed
Teal is the weights (2022-03-02), grey ticks are repo commits.
Models › DialoGPT-medium family
DialoGPT-medium
Text in, text out, 1K tokens of context.
Verified 2026-10-25 Rank #274 in LLMs · score 84.8 method v1 Sources 3 Downloads 30d 174.3k · #265 of 619 tracked
Do people use it?174.3kdownloads, 30 days#265 of 619 we track · top 43%+3 likes, downloads −12% this week449 likesHugging Face2026-10-24
Worth reading
Picked by rule from 1 tracked piece: the lab's own post, the most shared, a field report, the latest.
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: 3 quantized builds and 100 Spaces.
- As a service0no API provider listed
- On own hardware3quantized builds
- Built on12893 fine-tunes · 35 adapters · 0 merges
- In apps100+Hugging Face Spaces
Top Spaces running it: microsoft/HuggingGPT ♥ 2,272 · gunship999/SexyImages ♥ 439 · llamameta/flux-pro-uncensored ♥ 160 · Uthar/SexyReality ♥ 142
What people built on it
131 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
131 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
16 fields
Listed in LLMs
Facts
- 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 |
| 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.
All variants
40 variants
Lineage
finetune: 93quantized: 3adapter: 35
Top variants (40 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| sudeshmu/fine_tune | finetune | — | — | — | mit | sudeshmu | 9 | 1.4k |
| Fu01978/DialoGPT-medium-GGUF | quantized | GGUF | — | — | mit | Fu01978 | 0 | 1.9k |
| bachvnju/dialogptvn | finetune | — | 355M | S | — | bachvnju | 0 | 1.7k |
| pineappleSoup/DialoGPT-medium-707 | finetune | — | — | — | mit | pineappleSoup | 0 | 1.7k |
| Wildstash/DentalGPT | adapter | — | — | — | apache-2.0 | Wildstash | 17 | 26 |
| DineshKasi/ai-assistant | finetune | — | 406M | S | — | DineshKasi | 0 | 769 |
| Fu01978/DialoGPT-medium-distill-Kimi-K2-Instruct | finetune | — | 406M | S | mit | Fu01978 | 0 | 728 |
| sebastiantrbl/DialoGPT-daily-dialog-txt | finetune | — | — | — | mit | sebastiantrbl | 0 | 696 |
| sebastiantrbl/DialoGPT-finetuned-daily-dialog | finetune | — | — | — | mit | sebastiantrbl | 0 | 687 |
| kousik-2310/intent-classifier-minilm | quantized | — | 22.7M | S | apache-2.0 | kousik-2310 | 1 | 589 |
| Komala/new_DialoGPT-medium | finetune | — | 355M | S | mit | Komala | 0 | 619 |
| Gasolinaaa/dialogpt-empathetic-new | finetune | — | 355M | S | mit | Gasolinaaa | 0 | 593 |
| sebastiantrbl/test-DialoGPT-finetune | finetune | — | — | — | mit | sebastiantrbl | 0 | 570 |
| Komala/HPv5_DialoGPT-medium | finetune | — | 355M | S | mit | Komala | 0 | 538 |
| Komala/DialoGPT-medium | finetune | — | 355M | S | mit | Komala | 0 | 536 |
| stefaniftime/tmp93avx00w | finetune | — | — | — | mit | stefaniftime | 0 | 522 |
| stefaniftime/tmpnk87cy75 | finetune | — | — | — | mit | stefaniftime | 0 | 519 |
| reuben256/tmp_e77mr4r | finetune | — | — | — | mit | reuben256 | 0 | 477 |
| bhushanrocks/supportpal-dialoGPT-v3 | finetune | — | 355M | S | mit | bhushanrocks | 1 | 411 |
| schnabear/DialoGPT-medium-FinalFantasyDialogue | finetune | — | — | — | mit | schnabear | 0 | 429 |
| evinai/diablo_gpt | finetune | — | 355M | S | mit | evinai | 0 | 415 |
| shanthi-323/fine_tuned_model_dialogpt | finetune | — | 355M | S | — | shanthi-323 | 0 | 368 |
| sebastiantrbl/DialoGPT-conversation-dataset | finetune | — | — | — | mit | sebastiantrbl | 0 | 366 |
| sweatSmile/DialoGPT-FinTech-Investment-Banking-Assistant | adapter | — | 355M | S | mit | sweatSmile | 2 | 213 |
| cyril21/breakfree-dialo-lora | adapter | — | — | — | — | cyril21 | 0 | 296 |
| sebastiantrbl/DialoGPT-dailydialog-6 | finetune | — | — | — | mit | sebastiantrbl | 0 | 264 |
| abhishekmaroon5/lex-fridman-chatbot | finetune | — | 355M | S | mit | abhishekmaroon5 | 1 | 212 |
| senko-sleepy-fox/anime-senko-chat | finetune | — | 355M | S | mit | senko-sleepy-fox | 1 | 195 |
| Excalionidus/DialoGPT-medium-abridgedgoku | finetune | — | 355M | S | — | Excalionidus | 0 | 170 |
| DenTRM/test_chatbot | finetune | — | 355M | S | mit | DenTRM | 0 | 169 |
| arberbr/bill-nye-science-guy | adapter | — | — | — | apache-2.0 | arberbr | 0 | 158 |
| adanal/dialogpt-finetuned | finetune | — | 355M | S | mit | adanal | 0 | 149 |
| dChicago/calisthenics-v1-mini | adapter | GGUF | — | — | — | dChicago | 0 | 132 |
| Prajyotsna/relationship-chatbot-peft | adapter | — | — | — | mit | Prajyotsna | 0 | 131 |
| fiiamponsah/demo-restored-compliance-model | adapter | — | — | — | — | fiiamponsah | 0 | 130 |
| ajc2195/parks-llm | finetune | — | — | — | apache-2.0 | ajc2195 | 0 | 128 |
| Nik131104/SacrasticAhh | finetune | — | 355M | S | apache-2.0 | Nik131104 | 1 | 63 |
| sandylolpotty/s | adapter | — | — | — | apache-2.0 | sandylolpotty | 0 | 111 |
| romenlaw/DialoGPT-medium | finetune | — | 355M | S | apache-2.0 | romenlaw | 1 | 55 |
| ajc2195/parks-llm-v2 | finetune | — | 355M | S | apache-2.0 | ajc2195 | 0 | 105 |
Repository changelog
18 commits
Repository changelog 18 commits
| Date | Commit | SHA |
|---|---|---|
| 2024-02-29 | Fix Conversational Widget (#16) | 7b40bb0 |
| 2024-02-16 | Add default chat template to tokenizer_config.json (#15) | 8097fca |
| 2023-01-24 | Adding generation config file(s) | 9d5c5fa |
| 2021-05-23 | upload flax model | 8bada3b |
| 2021-05-23 | allow flax | bb39873 |
| 2021-02-23 | Create tokenizer_config.json | e84a3e0 |
| 2020-12-11 | Migrate model card from transformers-repo | adda561 |
| 2020-10-14 | Update config.json | 7cb5298 |
| 2020-06-28 | Update rust_model.ot | 8e2e228 |
| 2020-04-24 | Update config.json | a901f37 |
| 2020-04-11 | Update tf_model.h5 | b867618 |
| 2020-03-23 | Update config.json | 451955c |
| 2020-03-11 | Update config.json | e9ce49e |
| 2020-03-10 | Update pytorch_model.bin | 9aad463 |
| 2020-03-10 | Update vocab.json | 652ecc6 |
| 2020-03-10 | Update config.json | 0ca21e6 |
| 2020-03-10 | Update merges.txt | f68dda4 |
| 2020-03-10 | initial commit | cb79956 |
Articles and coverage
1 piece
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency.
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
- opt-125m same task (text-generation)
- gpt-j-6b same task (text-generation), permissive license
- Qwen-VL-Chat same task (text-generation)
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:37 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:07 UTC · Last verified 2026-10-25
Follow DialoGPT-medium
Watch this model
- /feeds/models/microsoft--DialoGPT-medium.xml(RSS 2.0) · every change to DialoGPT-medium
- /feeds/families/microsoft--DialoGPT-medium.xml(RSS 2.0) · every change across the DialoGPT-medium family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.