SAVRN
Search Contact SAVRN

Open-weight model

octomind-embed

by Muvon Un Limited muvon/octomind-embed

Embedding model for octomind capability / skill auto-activation: ibm-granite/granite-embedding-30m-english (30M params, 6 layers, 384-dim, CLS-pooled, prefix-free, English) fine-tuned on trigger phrases from the octomind-tap capabilities + skills catalog and…

Parameters30M
Context514
Weights272.4 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads4.8k

Runs On

What it takes to serve octomind-embed (30M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.1 GB 0.1 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.0 GB 0.0 GB 1x MI300X (192 GB)
Vultr
$1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.0 GB 0.0 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.

Model Card

By Muvon Un Limited, published under apache-2.0, revision 0d12ad93964c.

Embedding model for octomind capability / skill auto-activation: ibm-granite/granite-embedding-30m-english (30M params, 6 layers, 384-dim, CLS-pooled, prefix-free, English) fine-tuned on trigger phrases from the octomind-tap capabilities + skills catalog and blended back into the base as a WiSE-FT model soup, which beats both the base and the raw fine-tune on the runtime gate (mean-of-top-3 cosine + threshold + margin). CachedMultipleNegativesRankingLoss (scale 10) on in-class pairs and positive-aware hard-negative triplets, MatryoshkaLoss over [384, 256, 192, 128, 96], then weight interpolation with the base. - model.safetensors + 1Pooling/ — sentence-transformers layout (fp32).…

Read Muvon Un Limited's full model card

Embedding model for octomind capability / skill auto-activation: ibm-granite/granite-embedding-30m-english (30M params, 6 layers, 384-dim, CLS-pooled, prefix-free, English) fine-tuned on trigger phrases from the octomind-tap capabilities + skills catalog and blended back into the base as a WiSE-FT model soup, which beats both the base and the raw fine-tune on the runtime gate (mean-of-top-3 cosine + threshold + margin).

Training: rule-based + LLM paraphrase augmentation, one epoch of CachedMultipleNegativesRankingLoss (scale 10) on in-class pairs and positive-aware hard-negative triplets, MatryoshkaLoss over [384, 256, 192, 128, 96], then weight interpolation with the base.

Files

  • model.safetensors + 1_Pooling/ — sentence-transformers layout (fp32).
  • onnx/model.onnx — fp32 graph.
  • onnx/model_quantized.onnx — int8 (weight-only, reduce_range=True); this is what the octomind runtime loads. Pool with CLS as declared in 1_Pooling/config.json.

Use

octomind loads onnx:muvon/octomind-embed via octolib's ONNX provider (MODEL_NAME in octomind/src/embeddings/mod.rs). Runtime thresholds are model-specific and calibrated against the int8 graph (AUTO_ACTIVATE_THRESHOLD / _MARGIN in capability.rs, SEMANTIC_* in skill.rs).

Configuration

Architecture
RobertaModel
Context length (tokens)
514
Layers
6
Hidden size
384
Feed-forward size
1,536
Attention heads
12
Vocabulary size
50,265
Model type
roberta

Identity and Version

Repository
muvon/octomind-embed
Publisher
Muvon Un Limited
Task
Not stated by the source
Modality
Other
Library
sentence-transformers
Parameters
30M parameters
Languages
Not stated by the source
Revision
0d12ad93964c3e1a594509340194311638baecbd
First published
2026-05-12
Last updated
2026-09-18

Files and Weights

30 files, 282.5 MB in total. The weights are 4 files totalling 272.4 MB in bin, onnx, safetensors.

Weights4 files · 272.4 MB
Configuration13 files · 16.9 KB
Tokenizer10 files · 10.1 MB
Documentation1 file · 1.5 KB
Other1 file · 1.1 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights121.2 MB 000a1e47356a
onnx/model.onnxWeights120.7 MB 0f3475e1e633
onnx/model_quantized.onnxWeights30.5 MB ca5ba6a3e4e4
training_args.binWeights6.3 KB 6969afc457bc
1_Pooling/config.jsonConfiguration89 B
config.jsonConfiguration624 B
config_sentence_transformers.jsonConfiguration284 B
modules.jsonConfiguration429 B
onnx/1_Pooling/config.jsonConfiguration89 B
onnx/calibration.jsonConfiguration11.6 KB
onnx/config.jsonConfiguration624 B
onnx/config_sentence_transformers.jsonConfiguration284 B
onnx/modules.jsonConfiguration429 B
onnx/sentence_bert_config.jsonConfiguration241 B
onnx/special_tokens_map.jsonConfiguration957 B
sentence_bert_config.jsonConfiguration241 B
special_tokens_map.jsonConfiguration957 B
README.mdDocumentation1.5 KB
eval/Information-Retrieval_evaluation_holdout-ir_results.csvOther1.1 KB
.gitattributesRepository1.5 KB
merges.txtTokenizer456.3 KB
onnx/merges.txtTokenizer456.3 KB
onnx/tokenizer.jsonTokenizer3.6 MB
onnx/tokenizer_config.jsonTokenizer1.5 KB
onnx/vocab.jsonTokenizer798.3 KB
onnx/vocab.txtTokenizer231.5 KB
tokenizer.jsonTokenizer3.6 MB
tokenizer_config.jsonTokenizer1.5 KB
vocab.jsonTokenizer798.3 KB
vocab.txtTokenizer231.5 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
272.4 MB
Download from Muvon Un Limited

Released by Muvon Un Limited through its official repository on Hugging Face. Read the license.

Built From

  • Derived from ibm-granite/granite-embedding-30m-english
  • Quantized from ibm-granite/granite-embedding-30m-english

Memory Requirements

PrecisionWeights in memory
As published272.4 MB
16-bit0.1 GB
8-bit0.0 GB
4-bit0.0 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About octomind-embed

How much GPU memory does octomind-embed need?

About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (30M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run octomind-embed 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 octomind-embed commercially?

Yes. octomind-embed 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.

What is octomind-embed's context length?

514 tokens, from the maximum position embeddings in its published configuration.