The story so far
Weights, every dated article, and repo commits on one rail.
19 repo commits since the weights landed
Teal is the weights (2024-11-25), grey ticks are repo commits.
Models › Qwen2ForCausalLM-2.5 family
tiny-Qwen2ForCausalLM-2.5
trl-internal-testing Not declared out 23 months ago
2.44M parameters, text in, text out, 32K tokens of context.
Verified 2026-10-25 Rank #541 in LLMs · score 75.3 method v1 Sources 3 Downloads 30d 3M · #47 of 619 tracked
Do people use it?3Mdownloads, 30 days#47 of 619 we track · top 8%−10 likes, downloads −37% this week59 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: 1 quantized builds and 1 Spaces.
- As a service0no API provider listed
- On own hardware1quantized builds
- Built on63 fine-tunes · 3 adapters · 0 merges
- In apps1Hugging Face Spaces
Top Spaces running it: emanforhelp/model-pulse ♥ 5
What people built on it
7 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
7 derivatives on the Hub, led by 3 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.
What the card says
1 cited sentence
Summary generated, cited
The model serves as a minimal tool for unit tests within the TRL library.[1]
Generated 2026-10-07 15:10 UTC by parasail-gemma-4-26b-a4b-it; each numeral points at the fact it rests on. Not a verdict.
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.
Facts
19 fields
Listed in LLMs
Facts
- tiny-Qwen2ForCausalLM-2.5 has 2.44M parameters. (safetensors metadata, observed 2026-10-24)
- Context length is 32,768 tokens (32K). (config.json max_position_embeddings, observed 2026-10-24)
- License: Not declared (friction: review). No license declared on the model card. (license file, observed 2026-10-24)
- Created 2024-11-25, last modified 2026-09-08. (HF API, observed 2026-10-24)
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | Qwen2ForCausalLM |
| Model type | qwen2 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 2,435,016 |
| Size band | S |
| MoE | no |
| Context length | 32,768 (config.json max_position_embeddings) |
| License | Not declared |
| Hub snapshot | 2026-10-25 |
Servability
vLLM · SGLang
Servability
vLLM: supported · Qwen2ForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Qwen2ForCausalLM · 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 tiny-Qwen2ForCausalLM-2.5: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.0 GB · Edge (<4 GB) |
|---|---|
| FP8 (1 byte/param) | 0.0 GB · Edge (<4 GB) |
| INT4 (0.5 bytes/param) | 0.0 GB · Edge (<4 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
All variants
7 variants
Lineage
finetune: 3adapter: 3quantized: 1
Top variants (7 shown, ranked by downloads)
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| albertvillanova/test_training_with_generation_0 | finetune | — | 2.43M | S | — | albertvillanova | 0 | 88 |
| albertvillanova/test_training_with_generation_1 | finetune | — | 2.43M | S | — | albertvillanova | 0 | 72 |
| hubnemo/tiny-Qwen2ForCausalLM-2.5-lora | adapter | — | — | — | — | hubnemo | 0 | 40 |
| hubnemo/best-lora-ever | adapter | — | — | — | — | hubnemo | 0 | 40 |
| valerielucro/Qwen2-0.5B-GRPO_dummy | finetune | — | 2.43M | S | — | valerielucro | 0 | 36 |
| rajeshidimannan/newFTqwen2.5 | adapter | — | — | — | — | rajeshidimannan | 0 | 22 |
| haydso/tiny-Qwen2ForCausalLM-2.5-ONNX | quantized | — | — | — | — | haydso | 0 | 0 |
Repository changelog
19 commits
Repository changelog 19 commits
| Date | Commit | SHA |
|---|---|---|
| 2026-09-08 | Upload Qwen2ForCausalLM (#10) | ce8d0bf |
| 2025-12-19 | Upload config | 4b10ebe |
| 2025-12-19 | Upload Qwen2ForCausalLM | f56c2fb |
| 2025-12-09 | Upload config | 9ed7a8a |
| 2025-12-09 | Upload Qwen2ForCausalLM | 564a515 |
| 2025-09-24 | Upload Qwen2ForCausalLM | bd7a22d |
| 2025-09-23 | Upload Qwen2ForCausalLM | 8209630 |
| 2025-09-23 | Upload Qwen2ForCausalLM | 6d29498 |
| 2025-09-23 | Upload Qwen2ForCausalLM | 4582191 |
| 2025-08-02 | Upload Qwen2ForCausalLM | c837622 |
| 2025-06-14 | Upload tokenizer | 7412562 |
| 2025-06-14 | Upload Qwen2ForCausalLM | 54f7fa5 |
| 2025-06-14 | Upload tokenizer | abfa104 |
| 2025-06-14 | Upload tokenizer | 942bbf3 |
| 2025-06-14 | Upload tokenizer | 8913f58 |
| 2024-11-25 | Upload README.md with huggingface_hub | 6cee29c |
| 2024-11-25 | Upload tokenizer | e516153 |
| 2024-11-25 | Upload Qwen2ForCausalLM | 271d698 |
| 2024-11-25 | initial commit | 202c406 |
Similar models
3 models
Similar models
- Ornith-1.0-9B · 1.47M same size band (S), same task (text-generation), more providers, permissive license
- opt-125m same task (text-generation)
- gpt-j-6b same task (text-generation), permissive license
Sources
3 sources
Sources
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:39 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:46 UTC · Summary: 2026-10-07 15:10 UTC · Last verified 2026-10-25
Follow tiny-Qwen2ForCausalLM-2.5
Watch this model
- /feeds/models/trl-internal-testing--tiny-Qwen2ForCausalLM-2.5.xml(RSS 2.0) · every change to tiny-Qwen2ForCausalLM-2.5
- /feeds/families/trl-internal-testing--Qwen2ForCausalLM-2.5.xml(RSS 2.0) · every change across the Qwen2ForCausalLM-2.5 family
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.