Up to date
shibing624 Apache 2.0 out 5 years ago
102M parameters, text in, embeddings out, 512 tokens of context. 2 providers serve it from $0.005 per million input tokens.
Verified 2026-10-25 Rank #48 in Embeddings · score 89.8 method v1 Sources 3 Downloads 30d 909k · #120 of 619 tracked
Picked by rule from 9 tracked pieces: the lab's own post, the most shared, a field report, the latest.
The 1 pick above, plus these 8. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
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.
Served by 2 API providers.
Top Spaces running it: qingxu98/gpt-academic ♥ 435 · shibing624/text2vec ♥ 36 · hahahafofo/ChatGLM-Chinese-Summary ♥ 8 · shibing624/similarities ♥ 5
Weights only, an estimate: leave room for the KV cache. Method
About 0.1 GB at INT4, 0.1 GB at FP8, 0.2 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 1 dated article (each links to it), grey ticks are repo commits.
5 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.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported Model speed up | 0.32 | shibing624/text2vec-base-chinese (fp32, baseline) | model author | 2026-10-07 |
| author-reported Model speed up | 0.32 | shibing624/text2vec-base-chinese (onnx-O4) | model author | 2026-10-07 |
| author-reported Model speed up | 0.32 | shibing624/text2vec-base-chinese (ov) | model author | 2026-10-07 |
| author-reported Model speed up | 0.31 | shibing624/text2vec-base-chinese (ov-qint8) | model author | 2026-10-07 |
| author-reported chinese text matching task | 31.93 | shibing624/text2vec-base-chinese | model author | 2026-10-07 |
| author-reported chinese text matching task | 42.67 | shibing624/text2vec-base-chinese | model author | 2026-10-07 |
| author-reported chinese text matching task | 70.16 | shibing624/text2vec-base-chinese | model author | 2026-10-07 |
| author-reported chinese text matching task | 17.21 | shibing624/text2vec-base-chinese | model author | 2026-10-07 |
| author-reported chinese text matching task | 79.3 | shibing624/text2vec-base-chinese | model author | 2026-10-07 |
| author-reported chinese text matching task | 70.27 | shibing624/text2vec-base-chinese | model author | 2026-10-07 |
| author-reported chinese text matching task | 50.42 | shibing624/text2vec-base-chinese | model author | 2026-10-07 |
| author-reported chinese text matching task | 51.61 | shibing624/text2vec-base-chinese | model author | 2026-10-07 |
The model maps sentences to a 768 dimensional dense vector space for semantic search and text matching.[1]
Generated 2026-10-07 15:04 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 Embeddings
| Pipeline tag | sentence-similarity |
|---|---|
| Library | sentence-transformers |
| Architectures | BertModel |
| Model type | bert |
| Dtype | float32 |
| Params by dtype | F32: 102,267,648 · I64: 512 |
| Size band | S |
| MoE | no |
| Context length | 512 (config.json max_position_embeddings) |
| Languages | zh |
| License | Apache 2.0 (apache-2.0) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · BertModel · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · BertModel · 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 text2vec-base-chinese: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 0.2 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: 5
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| qinghuiwan/structural-isomorphism-v2-expanded | finetune | — | 102M | S | mit | qinghuiwan | 0 | 400 |
| xuanye/cosent-similarity-text2vec | finetune | — | 102M | S | apache-2.0 | xuanye | 0 | 348 |
| zhaizy/text2vec-base-chinese-finetuned-imdb | finetune | — | 102M | S | apache-2.0 | zhaizy | 0 | 325 |
| qinghuiwan/structural-isomorphism-v1 | finetune | — | 102M | S | mit | qinghuiwan | 0 | 300 |
| lixugang/ch_text_001 | finetune | — | 102M | S | apache-2.0 | lixugang | 0 | 52 |
| Date | Commit | SHA |
|---|---|---|
| 2024-11-14 | Update README.md | 183bb99 |
| 2024-11-14 | Update README.md | f42a51d |
| 2024-11-14 | Add exported onnx model 'model_qint8_avx512_vnni.onnx' (#30) | 2cb063b |
| 2024-11-14 | Add exported openvino model 'openvino_model.xml' (#27) | ec6ced0 |
| 2024-11-14 | Add exported onnx model 'model_O4.onnx' (#29) | a446177 |
| 2024-04-03 | Adding `safetensors` variant of this model (#23) | 4aedd18 |
| 2024-02-19 | Update README.md | 8a8006b |
| 2024-02-19 | Update README.md | 74f7ae8 |
| 2023-08-28 | Adding ONNX file of this model (#12) | 8acc128 |
| 2023-06-22 | Update README.md | 26420fd |
| 2023-06-22 | Update README.md | c442ae6 |
| 2023-06-22 | Update README.md | b606b56 |
| 2023-06-05 | Update README.md | 630e10f |
| 2023-05-08 | utilize sentence_transformers (#4) | 2748ce5 |
| 2023-04-23 | Modify a small descriptive mistake in the usage example (#2) | ddfba58 |
| 2022-11-23 | Update README.md | 13ee917 |
| 2022-03-14 | Update README.md | b455bb0 |
| 2022-03-14 | Update README.md | 01b324a |
| 2022-03-14 | Update README.md | 59577b3 |
| 2022-03-07 | Update README.md | 01c2dee |
| 2022-01-29 | update cosent | 59e85aa |
| 2022-01-29 | Update README.md | 66c9560 |
| 2022-01-23 | Create README.md | d6fb8b9 |
| 2022-01-23 | Upload pytorch_model.bin with git-lfs | 53da5f4 |
| 2022-01-23 | Upload special_tokens_map.json | 4752ab1 |
| 2022-01-23 | Upload tokenizer_config.json | 55d7fff |
| 2022-01-23 | Upload vocab.txt | 0a25927 |
| 2022-01-23 | Upload logs.txt | 723ff60 |
| 2022-01-23 | Upload config.json | a966081 |
| 2022-01-23 | initial commit | e439aae |
Hosted endpoints observed for text2vec-base-chinese, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.0050/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfra deepinfra | shibing624/text2vec-base-chinese | 512 | — | $0.0050 | — | — | — | — | live | 2026-10-24 |
| HF Inference hf | shibing624/text2vec-base-chinese | — | — | — | — | — | — | — | live | 2026-10-25 |
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.
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:36 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:04 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.
