# mmbert-small-vi-exam-seq-labeling by Dao Minh: Open Model Source: https://savrn.com/models/mmbert-small-vi-exam-seq-labeling Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve mmbert-small-vi-exam-seq-labeling (308M 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 | 0.6 GB | 0.7 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.3 GB | 0.4 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.2 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 7, 2026. [mmbert-small-vi-exam-seq-labeling on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/mmbert-small-vi-exam-seq-labeling/gpus) ## Model Card By Dao Minh, published under mit, revision 7b3607a47e94. This model is a fine-tuned version of [jhu-clsp/mmBERT-base](https://savrn.com/models/mmbert-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0737 - Precision: 0.2997 - Recall: 0.5324 - F1: 0.3835 - Accuracy: 0.7187 ### Model description More information needed ### Intended uses & limitations More information needed ### Training and evaluation data More information needed ### Training procedure #### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 3e-05 - train_batch_size: 8 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 2 - gradient_accumulation_steps: 2 - total_train_batch_size: 32 - total_eval_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 0.1 - num_epochs: 4 - mixed_precision_training: Native AMP #### Training results [Read the full model card (173 words)](https://savrn.com/models/mmbert-small-vi-exam-seq-labeling/card) ## Configuration Architecture ModernBertForMaskedLM Context length (tokens) 8,192 Layers 22 Hidden size 768 Feed-forward size 1,152 Attention heads 12 Vocabulary size 256,000 Model type modernbert ## Identity and Version Repository daominhwysi/mmbert-small-vi-exam-seq-labeling Publisher Dao Minh Task Fill mask Modality Text Library transformers Parameters 308M parameters Languages Not stated by the source Revision 7b3607a47e94f9c25d6abb1db453cda8293433ad First published 2026-08-30 Last updated 2026-09-24 ## Files and Weights 32 files, 19.7 GB in total. The weights are 12 files totalling 19.7 GB in bin, pt, safetensors. Weights12 files · 19.7 GB Configuration13 files · 31.5 KB Tokenizer5 files · 34.4 MB Documentation1 file · 2.2 KB Repository1 file · 1.6 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | checkpoint-1000/model.safetensors | Weights | 1.2 GB | ff4e45e07ce5 | | checkpoint-1000/pytorch_model.bin | Weights | 1.2 GB | b6b8ac9b61fb | | checkpoint-1000/trainer_state.pt | Weights | 2.5 GB | c58058cf25f1 | | checkpoint-2000/model.safetensors | Weights | 1.2 GB | 6055c6ebe73b | | checkpoint-2000/pytorch_model.bin | Weights | 1.2 GB | c0692bba5234 | | checkpoint-2000/trainer_state.pt | Weights | 2.5 GB | 5a3617edf943 | | latest_checkpoint/model.safetensors | Weights | 1.2 GB | 91080399004e | | latest_checkpoint/pytorch_model.bin | Weights | 1.2 GB | feb02d212c3d | | latest_checkpoint/trainer_state.pt | Weights | 2.5 GB | d84121420152 | | model.safetensors | Weights | 1.2 GB | ea54809083aa | | pytorch_model.bin | Weights | 1.2 GB | feb02d212c3d | | trainer_state.pt | Weights | 2.5 GB | a0a8b26001ef | | checkpoint-1000/config.json | Configuration | 2.7 KB | — | | checkpoint-1000/enhanced_head_config.json | Configuration | 116 B | — | | checkpoint-1000/label_mapping.json | Configuration | 740 B | — | | checkpoint-2000/config.json | Configuration | 2.7 KB | — | | checkpoint-2000/enhanced_head_config.json | Configuration | 116 B | — | | checkpoint-2000/label_mapping.json | Configuration | 740 B | — | | config.json | Configuration | 2.7 KB | — | | enhanced_head_config.json | Configuration | 116 B | — | | label_mapping.json | Configuration | 740 B | — | | latest_checkpoint/config.json | Configuration | 2.7 KB | — | | latest_checkpoint/enhanced_head_config.json | Configuration | 116 B | — | | latest_checkpoint/label_mapping.json | Configuration | 740 B | — | | trainer_state.json | Configuration | 17.3 KB | — | | README.md | Documentation | 2.2 KB | — | | .gitattributes | Repository | 1.6 KB | — | | checkpoint-1000/tokenizer_config.json | Tokenizer | 564 B | — | | checkpoint-2000/tokenizer_config.json | Tokenizer | 564 B | — | | latest_checkpoint/tokenizer_config.json | Tokenizer | 564 B | — | | tokenizer.json | Tokenizer | 34.4 MB | cb7916382aa8 | | tokenizer_config.json | Tokenizer | 564 B | — | ## License and Download License mit Access Open weights, no gate Download size 19.7 GB [Download from Dao Minh](https://huggingface.co/daominhwysi/mmbert-small-vi-exam-seq-labeling) Released by Dao Minh through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Derived from [jhu-clsp/mmBERT-base](https://savrn.com/models/mmbert-base) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 19.7 GB | | 16-bit | 0.6 GB | | 8-bit | 0.3 GB | | 4-bit | 0.2 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About mmbert-small-vi-exam-seq-labeling ### How much GPU memory does mmbert-small-vi-exam-seq-labeling need? About 0.7 GB at 16-bit and 0.2 GB at 4-bit: the weights (308M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run mmbert-small-vi-exam-seq-labeling on? 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. ### Can I use mmbert-small-vi-exam-seq-labeling commercially? Yes. mmbert-small-vi-exam-seq-labeling is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included. ### What is mmbert-small-vi-exam-seq-labeling's context length? 8,192 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Fill mask ### [deberta-v2-large-japanese-char-wwm](https://savrn.com/models/deberta-v2-large-japanese-char-wwm) [Language Media Processing Lab at Kyoto University](https://savrn.com/model-publishers/ku-nlp) This is a Japanese DeBERTa V2 large model pre-trained on Japanese Wikipedia, the Japanese portion of CC-100, and the Japanese portion of OSCAR. This model is trained with character-level tokenization and whole word masking. You can use this model for masked language modeling as follows: You can also fine-tune this model on downstream tasks. There is no need to tokenize texts in advance, and you can give raw texts to the tokenizer. The texts are tokenized into character-level tokens by sentencepiece. We used the following corpora for pre-training: - Japanese Wikipedia (as of 20221020, 3.2GB, 27M sentences, 1.3M documents) - Japanese portion of CC-100 (85GB, 619M sentences, 66M documents)… Open weights cc-by-sa-4.0 330M parameters 512 tokens transformers [View model](https://savrn.com/models/deberta-v2-large-japanese-char-wwm) Model · Fill mask ### [xlm-roberta-base](https://savrn.com/models/xlm-roberta-base) [Facebook AI community](https://savrn.com/model-publishers/facebookai) XLM-RoBERTa model pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. It was introduced in the paper Unsupervised Cross-lingual Representation Learning at Scale by Conneau et al. and first released in this repository. Disclaimer: The team releasing XLM-RoBERTa did not write a model card for this model so this model card has been written by the Hugging Face team. XLM-RoBERTa is a multilingual version of RoBERTa. It is pre-trained on 2.5TB of filtered CommonCrawl data containing 100 languages. RoBERTa is a transformers model pretrained on a large corpus in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in… Open weights mit 279M parameters 514 tokens transformers [View model](https://savrn.com/models/xlm-roberta-base) Model · Fill mask ### [bert-large-uncased](https://savrn.com/models/bert-large-uncased) [BERT community](https://savrn.com/model-publishers/google-bert) Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is uncased: it does not make a difference between english and English. Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by the Hugging Face team. BERT is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from… Open weights apache-2.0 336M parameters 512 tokens transformers [View model](https://savrn.com/models/bert-large-uncased) Model · Fill mask ### [roberta-large](https://savrn.com/models/roberta-large) [Facebook AI community](https://savrn.com/model-publishers/facebookai) Pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is case-sensitive: it makes a difference between english and English. Disclaimer: The team releasing RoBERTa did not write a model card for this model so this model card has been written by the Hugging Face team. RoBERTa is a transformers model pretrained on a large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels… Open weights mit 355M parameters 514 tokens transformers [View model](https://savrn.com/models/roberta-large) Model · Fill mask ### [ModernBERT-large](https://savrn.com/models/modernbert-large) [Answer.AI](https://savrn.com/model-publishers/answerdotai) ModernBERT is a modernized bidirectional encoder-only Transformer model (BERT-style) pre-trained on 2 trillion tokens of English and code data with a native context length of up to 8,192 tokens. ModernBERT leverages recent architectural improvements such as: - Rotary Positional Embeddings (RoPE) for long-context support. - Local-Global Alternating Attention for efficiency on long inputs. - Unpadding and Flash Attention for efficient inference. ModernBERT’s native long context length makes it ideal for tasks that require processing long documents, such as retrieval, classification, and semantic search within large corpora. The model was trained on a large corpus of text and code, making it… Open weights apache-2.0 396M parameters 8,192 tokens transformers [View model](https://savrn.com/models/modernbert-large) Model · Fill mask ### [ModernBERT-Large-Instruct-Logician-v0.5](https://savrn.com/models/modernbert-large-instruct-logician-v0-5) [John Gorriceta](https://savrn.com/model-publishers/johngorri) This model is a fine-tuned version of ModernBERT optimized for logical reasoning, deductive analysis, and structure-based token prediction. It relies on the ModernBertForMaskedLM architecture, making it highly effective at filling in missing contextual logic tokens (fill-mask). - As an encoder-based Masked Language Model, it is not designed for long-form generative text (like ChatGPT). It excels at predicting masked tokens inside structured prompts. Open weights apache-2.0 396M parameters 8,192 tokens [View model](https://savrn.com/models/modernbert-large-instruct-logician-v0-5) ## Dao Minh [All models and datasets](https://savrn.com/model-publishers/daominhwysi) ## Versions - [7b3607a47e94](https://savrn.com/models/mmbert-small-vi-exam-seq-labeling/versions/7b3607a47e94) · current 2026-09-24 ## Explore More - [All fill mask models](https://savrn.com/models/tasks/fill-mask) - [All models under mit](https://savrn.com/models/licenses/mit) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-09-24. - [Hugging Face record](https://huggingface.co/daominhwysi/mmbert-small-vi-exam-seq-labeling) - [How the hub is built](https://savrn.com/model-hub/methodology)