SAVRN Model Hub · Comparisons
all-distilroberta-v1 vs text2vec-base-chinese
All-distilroberta-v1 has 82M parameters and text2vec-base-chinese has 102M parameters; both are released under Apache License 2.0; at 16-bit, all-distilroberta-v1 needs about 0.2 GB (1x MI300X from $1.85 an hour) and text2vec-base-chinese about 0.2 GB (1x MI300X from $1.85 an hour).
| Field | all-distilroberta-v1 sentence-transformers/all-distilroberta-v1 | text2vec-base-chinese shibing624/text2vec-base-chinese |
|---|---|---|
| Publisher | Sentence Transformers | Ming Xu (徐明) |
| Task | Sentence similarity | Sentence similarity |
| Modality | Text | Text |
| Parameters, as reported | 82M parameters | 102M parameters |
| Architecture | RobertaForMaskedLM | BertModel |
| Library | sentence-transformers | sentence-transformers |
| Context length | 514 tokens | 512 tokens |
| Repository size | 3.2 GB | 1.9 GB |
| Artifact formats | safetensors, onnx, openvino, pytorch, rust | safetensors, onnx, openvino, pytorch |
| License | apache-2.0 | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.2 GB | 0.2 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0 GB | 0.1 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | 842eaed40bee | 183bb99aa7af |
| Downloads reported by the hub | 2.7M | 993.4k |
| Last observed | 2026-09-18 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
SAVRN's Notes on all-distilroberta-v1
How much GPU does an 82M-parameter embedding model need? Almost none: 0.2 GB of weights at 16-bit, 0.1 GB at 8-bit, and the cheapest setup on our Index is one MI300X with 192 GB at $1.85 an hour, a card this model leaves nearly empty, so share it with other work. What you get is a 768-dimensional vector for each sentence or paragraph, meant for semantic search and clustering, inside a 514-token context, so anything longer gets chunked first.
Eight training sets are on record, among them s2orc, ms_marco, code_search_net, stackexchange_xml and eli5; ask whether your corpus looks like them. Apache 2.0 means shipping it inside a commercial product, modifying it and redistributing it are allowed once the license and notices are kept and changes stated. Download only the format you need: the 3.19 GB across 30 files spans safetensors, onnx, openvino, pytorch and rust, and one is enough.
SAVRN's Notes on text2vec-base-chinese
Five hundred twelve tokens is the number to keep in view. It embeds Chinese sentences into a 768-dimensional vector, trained with CoSENT on hfl/chinese-macbert-base using the shibing624/nli_zh data, so it suits sentence pairs rather than long documents. Its 102 million parameters load in 0.2 GB at 16-bit. The cheapest accelerator in our table, one MI300X with 192 GB at $1.85 per hour on-demand, is beside the point; the ONNX and OpenVINO exports let a CPU node serve it and keep the GPU for the model that answers.
Apache 2.0 allows commercial use, so a Chinese search index is clear once the notices ride along. Anything past 512 tokens must be chunked, and the chunking will matter more than the model choice. Released March 2, 2022 and updated November 14, 2024, with no reported evaluations and no host prices in the SAVRN Index, so test on your own domain.
Questions
Which is larger, all-distilroberta-v1 or text2vec-base-chinese?
text2vec-base-chinese (102M parameters) is larger than all-distilroberta-v1 (82M parameters), by the parameter counts their publishers report.
Which is cheaper to run, all-distilroberta-v1 or text2vec-base-chinese?
At 4-bit, all-distilroberta-v1 fits on 1x MI300X from $1.85 an hour and text2vec-base-chinese on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use all-distilroberta-v1 commercially?
Yes. all-distilroberta-v1 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Can I use text2vec-base-chinese commercially?
Yes. text2vec-base-chinese is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.