Feature Extraction
Transformers
Safetensors
llama
financial
transactions
foundation-model
embeddings
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("simonykq/nvidia-transaction-decoder-fm", device_map="auto")Quick Links
NVIDIA Transaction Decoder Foundation Model (~29M)
Pretrained checkpoint from the NVIDIA Build Your Own Transaction Foundation Model developer example, as described in the NVIDIA Technical Blog.
- Architecture: Llama decoder-only (~29M params, hidden 512, 8 layers, GQA)
- Vocabulary: ~6,251 domain-specific financial transaction tokens
- Trained ~3,000 steps on IBM TabFormer with NeMo AutoModel
- Load with
AutoModelForCausalLM.from_pretrained(...)and extract last-token embeddings
This Hub mirror exists so Spaces / Transformers can load the Git LFS checkpoint published under models/decoder-foundation-model/ in the upstream GitHub repo.
- Downloads last month
- 11
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="simonykq/nvidia-transaction-decoder-fm")