Skip to main content
RECOGNITION · PROGRAMMES · ECOSYSTEM · TRUST FinanceGPT Developers
Listed on NVIDIA MarketplaceEnterprise Applications · Verify listing
Trust Center FinanceGPT applications
FinanceGPT Model Hub

all-MiniLM-L6-v2

Pinned FinanceGPT semantic transformer runtime with immutable revision, verified artifact hash and local inference provenance.

sentence-transformers/all-MiniLM-L6-v2 · ea78891063587eb050ed4166...
Try inference API All models
Overview Quickstart APIs SDKs Models Agents & tools Resources
Overview Files Inference Evaluate Versions Trust

Use this model

Copy-ready examples use the exact pinned revision and keep remote-code execution disabled.

transformers

from transformers import AutoModel, AutoTokenizer

repo = "sentence-transformers/all-MiniLM-L6-v2"
tokenizer = AutoTokenizer.from_pretrained(
    repo,
    revision="ea78891063587eb050ed4166b20062eaf978037c",
    trust_remote_code=False,
)
model = AutoModel.from_pretrained(
    repo,
    revision="ea78891063587eb050ed4166b20062eaf978037c",
    use_safetensors=True,
    trust_remote_code=False,
)

sentence transformers

from sentence_transformers import SentenceTransformer

model = SentenceTransformer(
    "sentence-transformers/all-MiniLM-L6-v2",
    revision="ea78891063587eb050ed4166b20062eaf978037c",
)
embeddings = model.encode(["Operating cash flow increased year over year."], normalize_embeddings=True)

huggingface hub

from huggingface_hub import snapshot_download

path = snapshot_download(
    repo_id="sentence-transformers/all-MiniLM-L6-v2",
    revision="ea78891063587eb050ed4166b20062eaf978037c",
)
Task
feature-extraction
Transformer
Library
sentence-transformers
Developer loader
Weights
Safetensors
Distribution format
Hosted inference
Configured
Governed preview

What can I do with this model?

Advanced HF capabilities are now actions in model context rather than separate top-level destinations.
Pipeline

Use the task through a familiar Transformers-style pipeline.

Fine-tune

Open adapter and PEFT recipes pinned to this exact base model.

Optimize

Review ONNX, INT8 and supported quantization/export recipes.

Reproduce

Download the pinned snapshot and exact dependency guidance.

Model details

The identity and provenance developers need most often, without making the page a metadata inventory.
JSON manifest
Repository ID
sentence-transformers/all-MiniLM-L6-v2
Revision
ea78891063587eb050ed4166b20062eaf978037c
License
Apache-2.0
Artifact SHA-256
997404dcf8e7ea89cdf598ebab9594ec77c94a08f80861e4beece2c0d06d0b6d

Evaluation & runtime status

Public evaluation appears only when sealed to the exact model. Hosted inference remains a separate governed runtime capability.
Public evaluation
No public sealed evaluation
No public sealed evaluation card is asserted for this transformer reference.
View evaluation evidence →
Hosted inference
Configured; runtime unavailable
Open inference →

Advanced provenance & governance

Deep trust, files, dependency and governance evidence remains available without dominating the primary developer journey.
Inspect trust
FilesVersionsDependenciesTrust
Developer distribution and inference previews do not grant production, policy, QLM rebinding or Financial Actions authority. Those controls remain separate.