Zum Inhalt springen
ModelAufgelistetExtern
Herunterladen

TinyLLaVA SmolLM2 135M Instruct Dinov2 Small Finetuned

| Category | # Samples | Accuracy | | Overall | 900 | 0.250 | | Overall-Art and Design | 120 | 0.217 | | Art | 30 | 0.167 | | Art Theory | 30 | 0.267 | | Design | 30 | 0.300 | | Music | 30 | 0.133 | |...

ArtText modelBasismodellHuggingFaceTB/SmolLM2-135M-InstructVersionmodelBBewertung

Modellquelle

Art
Text model
Dateigröße
300 MB
Basismodell
HuggingFaceTB/SmolLM2-135M-Instruct
Version
vmodel
Aktualisiert
4. Okt. 2026
Downloads
47
Quelle
Hugging Face

Quellenbeschreibung

Finetuned, 500 epochs

MMMU

Category# SamplesAccuracy
Overall9000.250
Overall-Art and Design1200.217
Art300.167
Art Theory300.267
Design300.300
Music300.133
Overall-Business1500.300
Accounting300.367
Economics300.300
Finance300.300
Management300.267
Marketing300.267
Overall-Science1500.227
Biology300.200
Chemistry300.167
Geography300.267
Math300.267
Physics300.233
Overall-Health and Medicine1500.293
Basic Medical Science300.400
Clinical Medicine300.167
Diagnostics and Laboratory Med.300.267
Pharmacy300.300
Public Health300.333
Overall-Humanities and Soc. Sci.1200.267
History300.167
Literature300.233
Sociology300.367
Psychology300.300
Overall-Tech and Engineering2100.210
Agriculture300.200
Architecture and Engineering300.200
Computer Science300.200
Electronics300.167
Energy and Power300.167
Materials300.267
Mechanical Engineering300.267

Quellen

1 Quelle
Hugging FacePrimärVersion bf815de878a03b8ab67dc9d3a9fd8b91de20b31b
huggingface.co/sbrzz/TinyLLaVA-SmolLM2-135M-Instruct-dinov2-small-finetuned/tree/bf815de878a03b8ab67dc9d3a9fd8b91de20b31b

Verifiziert 21. Aug.

Modellartefakte

1 Artefakt

model.safetensors

safetensors · 300 MB · SHA-256 98b8b99db344…7424 · Hugging Face

Download file

Quellenauszüge

2 Auszüge

--- license: apache-2.0 language: - en base_model: - HuggingFaceTB/SmolLM2-135M-Instruct - facebook/dinov2-small pipeline_tag: visual-question-answering tags: - tinyllava --- Finetuned, 500 epochs [MMMU](https://tinyllava-factory.readthedocs.io/en/latest/Evaluation.html#mmmu) | Category | # Samples | Accuracy | |---------------------------------|-----------|----------| | Overall | 900 | 0.250 | | Overall-Art and Design | 120 | 0.217 | | Art | 30 | 0.167 | | Art Theory | 30 | 0.267 | | Design | 30 | 0.300 | | Music | 30 | 0.133 | | Overall-Business | 150 | 0.300 | | Accounting | 30 | 0.367 | | Economics | 30 | 0.300 | | Finance | 30 | 0.300 | | Management | 30 | 0.267 | | Marketing | 30 | 0.267 | | Overall-Science | 150 | 0.227 | | Biology | 30 | 0.200 | | Chemistry | 30 | 0.167 | | Geography | 30 | 0.267 | | Math | 30 | 0.267 | | Physics | 30 | 0.233 | | Overall-Health and Medicine | 150 | 0.293 | | Basic Medical Science | 30 | 0.400 | | Clinical Medicine | 30 | 0.167 | | Diagnostics and Laboratory Med. | 30 | 0.267 | | Pharmacy | 30 | 0.300 | | Public Health | 30 | 0.333 | | Overall-Humanities and Soc. Sci.| 120 | 0.267 | | History | 30 | 0.167 | | Literature | 30 | 0.233 | | Sociology | 30 | 0.367 | | Psychology | 30 | 0.300 | | Overall-Tech and Engineering | 210 | 0.210 | | Agriculture | 30 | 0.200 | | Architecture and Engineering | 30 | 0.200 | | Computer Science | 30 | 0.200 | | Electronics | 30 | 0.167 | | Energy and Power | 30 | 0.167 | | Materials | 30 | 0.267 | | Mechanical Engineering | 30 | 0.267 |

Source context: 47 downloads · 0 likes · Pipeline visual-question-answering · Repo sbrzz/TinyLLaVA-SmolLM2-135M-Instruct-dinov2-small-finetuned