SAVRN
Search Contact SAVRN

Open-weight model · Question answering

EraX-VL-7B-V2.0-Preview-i1-GGUF

by Team Mradermacher mradermacher/EraX-VL-7B-V2.0-Preview-i1-GGUF

weighted/imatrix quants of https://huggingface.co/erax-ai/EraX-VL-7B-V2.0-Preview For a convenient overview and download list, visit our model page for this model.

Parameters
Context
Weights89.0 GB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1.8k

Model Card

By Team Mradermacher, published under apache-2.0, revision 0b595742294e.

weighted/imatrix quants of https://huggingface.co/erax-ai/EraX-VL-7B-V2.0-Preview For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/EraX-VL-7B-V2.0-Preview-GGUF This is a vision model - mmproj files (if any) will be in the static repository. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on…

Read Team Mradermacher's full model card

About

weighted/imatrix quants of https://huggingface.co/erax-ai/EraX-VL-7B-V2.0-Preview

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/EraX-VL-7B-V2.0-Preview-GGUF

This is a vision model - mmproj files (if any) will be in the static repository.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF i1-IQ1_S 2.0 for the desperate
GGUF i1-IQ1_M 2.1 mostly desperate
GGUF i1-IQ2_XXS 2.4
GGUF i1-IQ2_XS 2.6
GGUF i1-IQ2_S 2.7
GGUF i1-IQ2_M 2.9
GGUF i1-Q2_K_S 2.9 very low quality
GGUF i1-Q2_K 3.1 IQ3_XXS probably better
GGUF i1-IQ3_XXS 3.2 lower quality
GGUF i1-IQ3_XS 3.4
GGUF i1-Q3_K_S 3.6 IQ3_XS probably better
GGUF i1-IQ3_S 3.6 beats Q3_K*
GGUF i1-IQ3_M 3.7
GGUF i1-Q3_K_M 3.9 IQ3_S probably better
GGUF i1-Q3_K_L 4.2 IQ3_M probably better
GGUF i1-IQ4_XS 4.3
GGUF i1-IQ4_NL 4.5 prefer IQ4_XS
GGUF i1-Q4_0 4.5 fast, low quality
GGUF i1-Q4_K_S 4.6 optimal size/speed/quality
GGUF i1-Q4_K_M 4.8 fast, recommended
GGUF i1-Q4_1 5.0
GGUF i1-Q5_K_S 5.4
GGUF i1-Q5_K_M 5.5
GGUF i1-Q6_K 6.4 practically like static Q6_K

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.

Identity and Version

Repository
mradermacher/EraX-VL-7B-V2.0-Preview-i1-GGUF
Publisher
Team Mradermacher
Task
Question answering
Modality
Text
Library
transformers
Parameters
Not stated by the source
Languages
vi, en, zh
Revision
0b595742294e516f15685d8515f585ed355afaf2
First published
2025-01-12
Last updated
2025-07-11

Files and Weights

27 files, 89.0 GB in total. The weights are 24 files totalling 89.0 GB in gguf.

Weights24 files · 89.0 GB
Documentation1 file · 6.3 KB
Other1 file · 4.5 MB
Repository1 file · 3.4 KB
Every file
FileTypeSizeSHA-256
EraX-VL-7B-V2.0-Preview.i1-IQ1_M.ggufWeights2.0 GB 9181c83e9da7
EraX-VL-7B-V2.0-Preview.i1-IQ1_S.ggufWeights1.9 GB d656eed4dd31
EraX-VL-7B-V2.0-Preview.i1-IQ2_M.ggufWeights2.8 GB 51c7eb34971b
EraX-VL-7B-V2.0-Preview.i1-IQ2_S.ggufWeights2.6 GB efd478ee5e36
EraX-VL-7B-V2.0-Preview.i1-IQ2_XS.ggufWeights2.5 GB 5fae933cda17
EraX-VL-7B-V2.0-Preview.i1-IQ2_XXS.ggufWeights2.3 GB d6e0b5c16e38
EraX-VL-7B-V2.0-Preview.i1-IQ3_M.ggufWeights3.6 GB 8ce12fbb6fb9
EraX-VL-7B-V2.0-Preview.i1-IQ3_S.ggufWeights3.5 GB 0ee6645767d2
EraX-VL-7B-V2.0-Preview.i1-IQ3_XS.ggufWeights3.3 GB 7e82b4fcc8c4
EraX-VL-7B-V2.0-Preview.i1-IQ3_XXS.ggufWeights3.1 GB 70520aeeee8e
EraX-VL-7B-V2.0-Preview.i1-IQ4_NL.ggufWeights4.4 GB 1b4b23a86412
EraX-VL-7B-V2.0-Preview.i1-IQ4_XS.ggufWeights4.2 GB 218315de4e58
EraX-VL-7B-V2.0-Preview.i1-Q2_K.ggufWeights3.0 GB 4b656c3236c7
EraX-VL-7B-V2.0-Preview.i1-Q2_K_S.ggufWeights2.8 GB 943527edc56a
EraX-VL-7B-V2.0-Preview.i1-Q3_K_L.ggufWeights4.1 GB d90688611ac7
EraX-VL-7B-V2.0-Preview.i1-Q3_K_M.ggufWeights3.8 GB caefc0695223
EraX-VL-7B-V2.0-Preview.i1-Q3_K_S.ggufWeights3.5 GB d1a01d0ef056
EraX-VL-7B-V2.0-Preview.i1-Q4_0.ggufWeights4.4 GB 85e17c58b9ed
EraX-VL-7B-V2.0-Preview.i1-Q4_1.ggufWeights4.9 GB 430fbd9c5dec
EraX-VL-7B-V2.0-Preview.i1-Q4_K_M.ggufWeights4.7 GB b0f816d7d9ba
EraX-VL-7B-V2.0-Preview.i1-Q4_K_S.ggufWeights4.5 GB 5cef2734fd5b
EraX-VL-7B-V2.0-Preview.i1-Q5_K_M.ggufWeights5.4 GB 3c5bd68570cd
EraX-VL-7B-V2.0-Preview.i1-Q5_K_S.ggufWeights5.3 GB 90070aae1ec7
EraX-VL-7B-V2.0-Preview.i1-Q6_K.ggufWeights6.3 GB 7c26e1d702e0
README.mdDocumentation6.3 KB
imatrix.datOther4.5 MB fcfdfb788068
.gitattributesRepository3.4 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
89.0 GB
Download from Team Mradermacher

Released by Team Mradermacher through its official repository on Hugging Face. Read the license.

Built From

  • Derived from erax-ai/EraX-VL-7B-V2.0-Preview
  • Quantized from erax-ai/EraX-VL-7B-V2.0-Preview

Memory Requirements

PrecisionWeights in memory
As published89.0 GB

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

Questions About EraX-VL-7B-V2.0-Preview-i1-GGUF

Can I use EraX-VL-7B-V2.0-Preview-i1-GGUF commercially?

Yes. EraX-VL-7B-V2.0-Preview-i1-GGUF 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 · Question answering

splinter-base

Tel Aviv University

Splinter-base is the pretrained model discussed in the paper Few-Shot Question Answering by Pretraining Span Selection (at ACL 2021). Its original repository can be found here. The model is case-sensitive. Note: This model doesn't contain the pretrained weights for the QASS layer (see paper for details), and therefore the QASS layer is randomly initialized upon loading it. For the model with those weights, see tau/splinter-base-qass. Splinter is a model that is pretrained in a self-supervised fashion for few-shot question answering. 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…

Open weights apache-2.0 512 tokens transformers

This model can be used for the task of question answering. The model should not be used to intentionally create hostile or alienating environments for people. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. The model creators note in the associated paper: The model creators note in the associated paper: The model…

Open weights 512 tokens transformers

Model · Question answering

distilbert-onnx

Philipp Schmid

This model is a fine-tune checkpoint of DistilBERT-base-cased, fine-tuned using (a second step of) knowledge distillation on SQuAD v1.1. This model reaches a F1 score of 87.1 on the dev set (for comparison, BERT bert-base-cased version reaches a F1 score of 88.7).

Open weights apache-2.0 512 tokens transformers

Model · Question answering

roberta-base-on-cuad

Mohammed Rakib

This model can be used for the task of Question Answering on Legal Documents. Read: An Open Source Contractual Language Understanding Application Using Machine Learning for detailed information on training procedure, dataset preprocessing and evaluation. See CUAD dataset card for more information. See CUAD dataset card for more information. Used V100/P100 from Google Colab Pro Python, Transformers Mohammed Rakib in collaboration with Ezi Ozoani and the Hugging Face team Use the code below to get started with the model.

Open weights mit 514 tokens transformers