From: Alibaba-NLP <huggingface.co/Alibaba-NLP>Newsgroups: alt.freeweights.embedSubject:

GVE-7B

Date: 2026-11-14Commit: 3046045Signed: 2DC28CC7B26A283B ✓

Sentence similarity model with 8.3B parameters. Safetensors weights, 16.6 GB in all. Published by Alibaba-NLP under Apache-2.0.

8.3B params16.6GBGVE-7Bsafetensorspermissive

FactsParams8.3BSize16.6 GBFormatssafetensorsTasksentence similarityLicenseApache-2.0From sourcepermissive

$ fw get Alibaba-NLP/GVE-7B
# manifest sha256 7d163d66b6e1… · 16.6 GB · 21 files
$ fw verify ./GVE-7B Alibaba-NLP/GVE-7B

From sourceHosted (signed)Alibaba-NLP/GVE-7BLast check: 2026-11-14 21:07 UTC

Run at home Get help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Fine-tune of Qwen2.5-VL-7B-Instruct.

Works with

Run9 Fine-tune8 Convert8 Evaluate1 Scan2 Apps16

Runs with

Ranked by fit to this model (safetensors), then by GitHub stars.

Text Embeddings Inference

Transformers LocalAI tinygrad Triton Inference Server BentoML CTranslate2 ExLlamaV2 LitServe

Show all 16

sqlite-vec hnswlib pgvectorscale Infinity

Overview Model card Files Use it License Provenance Model tree

Overview

Size: 16.6 GB
Weights: 16.6 GB (safetensors)
Parameters: 8.3B
Formats: safetensors
Task: sentence similarity
License: Apache-2.0 (permissive)
Files: 21, each with a sha256
Publisher: Alibaba-NLP
Added: 2026-11-14
Section: alt.freeweights.embed

Lineage

Original release from the publisher.

Base model: Qwen/Qwen2.5-VL-7B-Instruct

Where these bytes come from

Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources

Badge	Host	Last check	Result
From source	huggingface.co	2026-11-14 21:07 UTC	passed

Model card

From the publisher at commit 3046045. Shown as plain text with links; images open at the publisher.

🎯 General Video Embedder (GVE)#

One Embedder for All Video Retrieval Scenarios Queries of text, image, video, or any combination modalities — GVE understands them all for representations, zero-shot, without in-domain training.

GVE is the first video embedding model that generalizes across 9 abilities, including 3 diverse retrieval tasks and 6 domains — from coarse text-to-video to fine-grained spatial/temporal queries, composed (text+image) queries, and long-context retrieval — all evaluated on our new Universal Video Retrieval Benchmark (UVRB).

Built on Qwen2.5-VL and trained only with LoRA with 13M collected and synthesized multimodal data, GVE achieves SOTA zero-shot performance than competitors.

🌟 Why GVE?#

Capability	Existing Works	GVE
Query Flexibility	Only text	✅ Text, ✅ Image, ✅ Video, ✅ Text+Image, ✅ Text+Video
Fine-grained Understanding	Weak on spatial-temporal details	S: 0.821, T: 0.469 (SOTA)
Training Data	Uses in-domain test data (e.g., MSRVTT)	Synthesized data — true zero-shot
Performance	Unite-7B (8.3B): 55.9	GVE-3B (3.8B): 0.571 → better with half the size; GVE-7B (3.8B): 0.600

📊 Performance on UVRB#

TXT: Textual Video Retrieval
CMP: Composed Video Retrieval
VIS: Visual Video Retrieval
CG: Coarse-grained Video Retrieval
FG: Fine-grained Video Retrieval
LC: Long-Context Video Retrieval
S: Spatial Video Retrieval
T: Temporal Video Retrieval
PR: Partially Relevant Video Retrieval

For each column: highest score is bolded, second-highest is underlined.

Model	AVG	TXT	CMP	VIS	CG	FG	LC	S	T	PR
CLIP4Clip	0.416	0.401	0.178	0.714	0.380	0.360	0.463	0.559	0.285	0.236
ViCLIP	0.375	0.336	0.263	0.640	0.380	0.315	0.313	0.484	0.289	0.171
VideoCLIP-XL	0.510	0.550	0.227	0.632	0.558	0.493	0.600	0.787	0.381	0.310
LanguageBind	0.508	0.543	0.231	0.645	0.539	0.479	0.610	0.723	0.378	0.336
InternVideo2-1B	0.420	0.422	0.248	0.581	0.480	0.403	0.383	0.606	0.413	0.189
InternVideo2-6B	0.445	0.448	0.220	0.660	0.504	0.417	0.423	0.631	0.400	0.220
GME-2B	0.416	0.539	0.345	0.597	0.461	0.471	0.685	0.716	0.349	0.347
Unite-2B	0.507	0.536	0.242	0.654	0.455	0.471	0.681	0.725	0.347	0.341
VLM2Vec-V2	0.538	0.587	0.263	0.613	0.498	0.502	0.762	0.809	0.348	0.348
BGE-VL	0.480	0.497	0.268	0.622	0.448	0.406	0.636	0.664	0.292	0.261
UniME-7B	0.542	0.561	0.308	0.702	0.500	0.518	0.664	0.785	0.396	0.373
B3-7B	0.538	0.570	0.270	0.678	0.482	0.505	0.722	0.797	0.364	0.355
GME-7B	0.562	0.604	0.341	0.615	0.518	0.507	0.788	0.749	0.373	0.398
Unite-7B	0.559	0.609	0.254	0.666	0.541	0.539	0.746	0.779	0.412	0.425
GVE-3B	0.571	0.619	0.304	0.647	0.552	0.541	0.764	0.816	0.430	0.377
GVE-7B	0.600	0.657	0.312	0.657	0.587	0.570	0.814	0.821	0.469	0.419

🚀 Get Started#

Loading model

model_path = 'Alibaba-NLP/GVE-7B'
model = AutoModel.from_pretrained(model_path, trust_remote_code=True, device_map='auto', low_cpu_mem_usage=True, torch_dtype=torch.bfloat16)
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True, use_fast=True)
processor.tokenizer.padding_side = 'left'

Processing inputs

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {
        "role": "user",
        "content": [
            {
                "type": "video",
                "video": "./asset/video_example.mp4",
                "max_pixels": 200 * 28 * 28,
                "fps": 1.0,
                "max_frames": 8,
            },
            {"type": "text", "text": "Describe this video."},
        ],
    }
]
texts = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True)
inputs = processor(
    text=[texts],
    images=image_inputs,
    videos=video_inputs,
    padding=True,
    truncation=True,
    max_length=1200,
    return_tensors="pt",
    **video_kwargs,
).to("cuda")

Embedding

outputs = model(**inputs)
embedding = F.normalize(outputs['last_hidden_state'][:, -1, :], p=2, dim=1)

📚 Citation#

@misc{guo2025gve,
  title={Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum}, 
  author={Zhuoning Guo and Mingxin Li and Yanzhao Zhang and Dingkun Long and Pengjun Xie and Xiaowen Chu},
  year={2025},
  eprint={2510.27571},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2510.27571}, 
}

Files

21 files · 16.6 GBWeights 16.6 GB (safetensors). Sizes and sha256 from the signed manifest.

Show all 21 files with their sha256

File	Size	sha256
.gitattributes	1.63 KB	a123bb5e00ab9bf70828aa37665e0a698cb9c99a4129e63a320a4ae890af0001
README.md	5.59 KB	a6f3b6c2186e3227f9af9251a3601510960745a24ff8ec8ad4d22ae68b826091
added_tokens.json	605 B	58b54bbe36fc752f79a24a271ef66a0a0830054b4dfad94bde757d851968060b
asset/video_example.mp4	628 KB	79f8e01809cf5d24cf04ed7745f7063fa4f60175729d393b084900e857cf102e
chat_template.json	1.05 KB	94174d7176c52a7192f96fc34eb2cf23c7c2059d63cdbfadca1586ba89731fb7
config.json	1.55 KB	5a27cddc9a524889fc4a8a07e39d65b9221d9823fe55a84d6a0aef9922adc3ac
demo.ipynb	3.35 KB	640e34d63a9cd4285c03f5d954b88529b0680d08a347e244f5532b387964bdd2
generation_config.json	214 B	bd0d7897e77a2c53fb4853c4918fa704b80ad501ea946468a6df8273f21d6727
merges.txt	1.67 MB	8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5
model-00001-of-00005.safetensors	4.04 GB	dacf32eee3d1044c3c9ac6281f7b85d5e08f6543ac5302ae8c8815bb6e7d28a5
model-00002-of-00005.safetensors	4.06 GB	03b090636a995b88ca46e015492f2eae5768057c80728dff84fd05f8494ef068
model-00003-of-00005.safetensors	4.00 GB	4510144d4c4e73171e39d74a2fdf63509b9196be60e3b677ee97af42b8933293
model-00004-of-00005.safetensors	3.40 GB	cc8c53250bc55ffca7dcde7e67551ecd724fe1275ee00bf0d9eec2d3ccdcb20e
model-00005-of-00005.safetensors	1.09 GB	0c859795ad3a627a9b95bcb762e059d5b768a4a36fdd4affeff269d93fdecc67
model.safetensors.index.json	57.6 KB	a9a1b35cda740d0e47ddeaaf07aadd04e3d561355f6e6ad657838070f4e03833
modeling_gve.py	9.48 KB	86e54f84b4b951a5e8c40c7648840b9b1bbcf89bde13c4c8a2da5d10f5f2f547
preprocessor_config.json	575 B	549c158011407dfb750d9ec578047cf76f5bfe365cd0aa069a50137d3f98d9dd
special_tokens_map.json	613 B	76862e765266b85aa9459767e33cbaf13970f327a0e88d1c65846c2ddd3a1ecd
tokenizer.json	11.4 MB	9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
tokenizer_config.json	5.78 KB	0a6be425d5d62ec1904deb45e569c809d0973bd39a411452388f268a855e3183
vocab.json	2.78 MB	ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910

VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.

Upstream commit	Date	Contents
3046045eee pinned now manifest updated, same commit	2026-11-14 21:07 UTC	21 files · 16.6 GB
3046045eee	2026-11-14 21:07 UTC	21 files · 16.6 GB

Use it

$ fw get Alibaba-NLP/GVE-7B
# manifest sha256 7d163d66b6e1… · 16.6 GB · 21 files
$ fw verify ./GVE-7B Alibaba-NLP/GVE-7B

fw.pyChecks the signature and every sha256, tries each source in order, resumes.

$ python3 fw.py get https://freeweights.allternit.com/manifests/Alibaba-NLP/GVE-7B.json --dir ./GVE-7B
$ python3 fw.py verify ./GVE-7B ./Alibaba-NLP__GVE-7B.json

hfThe Hugging Face CLI with one setting. Same repo id.

$ HF_ENDPOINT=https://freeweights.allternit.com hf download Alibaba-NLP/GVE-7B --revision 3046045eeed08e1d8731c3b943827b81b2b20817 --local-dir ./GVE-7B

transformersLoad the weights in Python.

import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModel, AutoTokenizer
tok = AutoTokenizer.from_pretrained("Alibaba-NLP/GVE-7B", revision="3046045eeed08e1d8731c3b943827b81b2b20817")
model = AutoModel.from_pretrained("Alibaba-NLP/GVE-7B", revision="3046045eeed08e1d8731c3b943827b81b2b20817", device_map="auto")

Run at home

License

Name: Apache License 2.0
Id: Apache-2.0
Class: Permissive
Redistribution: yes
Listing: Hosted (signed)
Decided: License as declared by the publisher. No person read it. 2026-11-14
Text in: README.md
Text sha256: a6f3b6c2186e3227f9af9251a3601510960745a24ff8ec8ad4d22ae68b826091
Terms gate: No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: Alibaba-NLP <huggingface.co/Alibaba-NLP>Newsgroups: alt.freeweights.embedSubject: GVE-7BDate: 2026-11-14Commit: 3046045Signed: 2DC28CC7B26A283B ✓

Upstream: Alibaba-NLP/GVE-7B
Pinned commit: 3046045eeed08e1d8731c3b943827b81b2b20817
Manifest: GVE-7B.json · .minisig
Manifest sha256: 7d163d66b6e1b9a5a4f88dce2cfa4e38c74aaa923b9f8f465d1f8acbaec1ee37
Signature: minisign, Ed25519, key 2DC28CC7B26A283B
Created: 2026-11-14 21:07 UTC
Generator: freeweights-manifest/0.1.0
Takedowns: None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/Alibaba-NLP/GVE-7B.json
$ curl -O https://freeweights.allternit.com/manifests/Alibaba-NLP/GVE-7B.json.minisig
$ minisign -Vm GVE-7B.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq
$ shasum -a 256 <file>   # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

Qwen/Qwen2.5-VL-7B-Instruct · this model is a finetune of it

No model in the catalog names this one as its parent.

Get it

Download

$ HF_ENDPOINT=https://freeweights.allternit.com hf download Alibaba-NLP/GVE-7B

Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest

minisign, key 2DC28CC7B26A283B. GVE-7B.json. Provenance. Takedown history: none.

Source

huggingface.co/Alibaba-NLP/GVE-7B

Related models

All of alt.freeweights.embed →

From: sentence-transformers <huggingface.co/sentence-transformers>Subject: all-MiniLM-L6-v1

From:

unsloth <huggingface.co/unsloth>Subject: all-MiniLM-L6-v2

From:

mlx-community <huggingface.co/mlx-community>Subject: all-MiniLM-L6-v2-4bit

From: sentence-transformers <huggingface.co/sentence-transformers>Subject: all-mpnet-base-v1

From: sentence-transformers <huggingface.co/sentence-transformers>Subject: allenai-specter

From: sentence-transformers <huggingface.co/sentence-transformers>Subject: bert-base-nli-max-tokens

GVE-7B

Works with

Runs with

Fine-tune with

Convert with

Evaluate with

Scan with

Works with

Overview

Model card

🎯 General Video Embedder (GVE)#

🌟 Why GVE?#

📊 Performance on UVRB#

🚀 Get Started#

📚 Citation#

Files

Use it

License

Provenance

How to verify

Model tree

Related models