# minerva-mlm-8k by Garyk Brixi: Open-Weight Model Source: https://savrn.com/models/minerva-mlm-8k Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve minerva-mlm-8k (671M 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 | 1.3 GB | 1.6 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 | 0.7 GB | 0.8 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 | 0.3 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 | 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. [minerva-mlm-8k on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/minerva-mlm-8k/gpus) ## Model Card By Garyk Brixi, published under apache-2.0, revision ee385d0b0b16. ### Minerva-MLM Minerva-MLM is a genome language model for coevolutionary mining. The checkpoint includes the masked language model head and three interaction heads for base-pairing, repeat, and structure signals. Full documentation, finetuning scripts, notebooks, and setup are on the [github](https://github.com/garykbrixi/minerva). [Try it in the browser here](https://huggingface.co/spaces/gbrixi/minerva). ### Checkpoints | Model | Context length | Hugging Face repo | | --- | --- | --- | | Minerva-MLM | 4,096 tokens | [gbrixi/minerva-mlm](https://savrn.com/models/minerva-mlm) | | Minerva-MLM-8k | 8,192 tokens | [gbrixi/minerva-mlm-8k](https://savrn.com/models/minerva-mlm-8k) | ### Install Inference from this repo needs only Transformers and PyTorch: ``` pip install "transformers>=4.41" torch safetensors pip install flash-attn # optional, recommended for production and packed sequences ``` flash-attn is picked up automatically when present, otherwise Minerva falls back to PyTorch SDPA. The optional minerva-dna package adds plotting helpers, GenBank utilities and finetuning wrappers, and lets you load the model without trust_remote_code: ``` pip install minerva-dna ``` ### Quick Start [Read the full model card (593 words)](https://savrn.com/models/minerva-mlm-8k/card) ## Configuration Architecture MinervaForMaskedLM Vocabulary size 37 Model type minerva ## Identity and Version Repository gbrixi/minerva-mlm-8k Publisher Garyk Brixi Task Fill mask Modality Text Library transformers Parameters 671M parameters Languages Not stated by the source Revision ee385d0b0b161be5b19856654cebdc118b43da7f First published 2026-05-26 Last updated 2026-10-05 ## Files and Weights 18 files, 2.7 GB in total. The weights are 1 file totalling 2.7 GB in safetensors. Weights1 file · 2.7 GB Configuration7 files · 205.4 KB Tokenizer2 files · 4.1 KB Documentation2 files · 17.8 KB Other5 files · 1.0 MB Repository1 file · 1.8 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 2.7 GB | 076ab8db1d21 | | config.json | Configuration | 1.9 KB | — | | constants.py | Configuration | 14.4 KB | — | | data.py | Configuration | 19.5 KB | — | | jacobian.py | Configuration | 32.8 KB | — | | modeling_minerva.py | Configuration | 88.3 KB | — | | special_tokens_map.json | Configuration | 833 B | — | | visualization.py | Configuration | 47.7 KB | — | | LICENSE | Documentation | 11.3 KB | — | | README.md | Documentation | 6.5 KB | — | | assets/minerva_banner_dark.webp | Other | 174.1 KB | f3ba92c1f5d1 | | assets/minerva_banner_light.webp | Other | 150.8 KB | 31eff6c9334f | | assets/minerva_owl_small.png | Other | 10.9 KB | — | | examples/TwoAYGGAY_Pseudomonas_fluorescens_SBW25.gb | Other | 601.6 KB | — | | examples/UG27_systems.gb | Other | 104.9 KB | — | | .gitattributes | Repository | 1.8 KB | — | | tokenizer.json | Tokenizer | 2.4 KB | — | | tokenizer_config.json | Tokenizer | 1.7 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 2.7 GB [Download from Garyk Brixi](https://huggingface.co/gbrixi/minerva-mlm-8k) Released by Garyk Brixi through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from [gbrixi/minerva-mlm](https://savrn.com/models/minerva-mlm) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 2.7 GB | | 16-bit | 1.3 GB | | 8-bit | 0.7 GB | | 4-bit | 0.3 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About minerva-mlm-8k ### How much GPU memory does minerva-mlm-8k need? About 1.6 GB at 16-bit and 0.4 GB at 4-bit: the weights (671M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run minerva-mlm-8k 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 minerva-mlm-8k commercially? Yes. minerva-mlm-8k 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. ## Similar Models Model · Fill mask ### [minerva-mlm](https://savrn.com/models/minerva-mlm) [Garyk Brixi](https://savrn.com/model-publishers/gbrixi) Minerva-MLM is a genome language model for coevolutionary mining. The checkpoint includes the masked language model head and three interaction heads for base-pairing, repeat, and structure signals. Full documentation, finetuning scripts, notebooks, and setup are on the github. Try it in the browser here. Inference from this repo needs only Transformers and PyTorch: flash-attn is picked up automatically when present, otherwise Minerva falls back to PyTorch SDPA. The optional minerva-dna package adds plotting helpers, GenBank utilities and finetuning wrappers, and lets you load the model without trustremotecode: With minerva-dna installed, import the class directly and drop trustremotecode… Open weights apache-2.0 671M parameters transformers [View model](https://savrn.com/models/minerva-mlm) Model · Fill mask ### [esm2_t33_650M_UR50D](https://savrn.com/models/esm2-t33-650m-ur50d) [AI at Meta](https://savrn.com/model-publishers/facebook) ESM-2 is a state-of-the-art protein model trained on a masked language modelling objective. It is suitable for fine-tuning on a wide range of tasks that take protein sequences as input. For detailed information on the model architecture and training data, please refer to the accompanying paper. You may also be interested in some demo notebooks (PyTorch, TensorFlow) which demonstrate how to fine-tune ESM-2 models on your tasks of interest. Several ESM-2 checkpoints are available in the Hub with varying sizes. Larger sizes generally have somewhat better accuracy, but require much more memory and time to train Open weights mit 652M parameters 1,026 tokens transformers [View model](https://savrn.com/models/esm2-t33-650m-ur50d) Model · Fill mask ### [xlm-roberta-large](https://savrn.com/models/xlm-roberta-large) [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 561M parameters 514 tokens transformers [View model](https://savrn.com/models/xlm-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) 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) ## Garyk Brixi [All models and datasets](https://savrn.com/model-publishers/gbrixi) ## Versions - [ee385d0b0b16](https://savrn.com/models/minerva-mlm-8k/versions/ee385d0b0b16) · current 2026-10-05 ## Explore More - [All fill mask models](https://savrn.com/models/tasks/fill-mask) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [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 2026-10-05. - [Hugging Face record](https://huggingface.co/gbrixi/minerva-mlm-8k) - [How the hub is built](https://savrn.com/model-hub/methodology)