Search public pages, research tools, and SAVRN solutions.
Open-weight model · Question answering
by Jangwon Park monologg/koelectra-base-v3-finetuned-korquad
What it takes to serve koelectra-base-v3-finetuned-korquad (112M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.2 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
The publisher has not written a card for this model.
7 files, 899.0 MB in total. The weights are 2 files totalling 898.8 MB in bin, safetensors.
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 449.4 MB | 75ad3ca646cd |
| pytorch_model.bin | Weights | 449.4 MB | f6d031e096e6 |
| config.json | Configuration | 591 B | — |
| special_tokens_map.json | Configuration | 112 B | — |
| .gitattributes | Repository | 399 B | — |
| tokenizer_config.json | Tokenizer | 111 B | — |
| vocab.txt | Tokenizer | 263.3 KB | — |
Released by Jangwon Park through its official repository on Hugging Face.
| Precision | Weights in memory |
|---|---|
| As published | 898.8 MB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (112M parameters) plus a working margin. A long context needs more.
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
512 tokens, from the maximum position embeddings in its published configuration.
This model was fine-tuned from the HuggingFace BERT base uncased checkpoint on SQuAD1.1. CPU: Intel(R) Core(TM) i7-6800K CPU @ 3.40GHz Memory: 32 GiB GPUs: 2 GeForce GTX 1070, each with 8GiB memory GPU driver: 418.87.01, CUDA: 10.1 It took about 2 hours to finish. Note that the above results didn't involve any hyperparameter search.
We trained a German question answering model with a gelectra-base model as its basis. - The dataset is GermanQuAD, a new, German language dataset, which we hand-annotated and published online. - The training dataset is one-way annotated and contains 11518 questions and 11518 answers, while the test dataset is three-way annotated so that there are 2204 questions and with 2204·3−76 = 6536answers, because we removed 76 wrong answers. See https://deepset.ai/germanquad for more details and dataset download in SQuAD format. Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on…
Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack: For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial. - Timo Möller: timo.moeller [at] deepset.ai deepset is the company behind the production-ready open-source AI framework Haystack. We also have a Discord community open to everyone!
Evaluated on the SQuAD 2.0 dev set with the official eval script. Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack: For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial. Vaishali Pal vaishali.pal [at] deepset.ai Timo Möller: timo.moeller [at] deepset.ai deepset is the company behind the production-ready open-source AI framework Haystack. We also have a Discord community open to everyone!
This is a BERT base cased model trained on SQuAD v2 Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack: For a complete example with an extractive question answering pipeline that scales over many documents, check out the corresponding Haystack tutorial. deepset is the company behind the production-ready open-source AI framework Haystack. We also have a Discord community open to everyone!
This is the roberta-base model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Extractive Question Answering. We have also released a distilled version of this model called deepset/tinyroberta-squad2. It has a comparable prediction quality and runs at twice the speed of deepset/roberta-base-squad2. Haystack is an AI orchestration framework to build customizable, production-ready LLM applications. You can use this model in Haystack to do extractive question answering on documents. To load and run the model with Haystack: For a complete example with an extractive question answering pipeline that scales over…