Text Classification
Transformers
ONNX
Safetensors
MLX
English
tamev
decision-model
decision-engine
llm-router
router
option-selection
intent-routing
tool-call-gating
agent-routing
system-one
multiple-choice
multiclass-classification
safety-guardrails
guardrails
calibration
probability-calibration
temperature-scaling
brier-score
expected-calibration-error
typesafe
jev-alternative
kev-alternative
edge-ai
offline-inference
tinybert
permutation-invariant
permutation-equivariant
onnxruntime
cpu-inference
onnx-int8
quantized
mps
torchscript
apple-silicon
metal
custom_code
Eval Results (legacy)
Instructions to use Tamkimd/tamev-nano-tinybert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Tamkimd/tamev-nano-tinybert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Tamkimd/tamev-nano-tinybert", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Tamkimd/tamev-nano-tinybert", trust_remote_code=True, device_map="auto") - MLX
How to use Tamkimd/tamev-nano-tinybert with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Tamkimd/tamev-nano-tinybert --local-dir tamev-nano-tinybert
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Commit History
-
Ship the accepted nano head (gate nano_cross_fusion_agfix_mps_hf) with the runtimes and card re-derived from those bytes
Verified signature9ff69d6
-
Publish TAMEV-Nano: audited weights with runtimes exported from the same architecture, model card and benchmarks regenerated from the measured held-out evaluation
Verified signature55107db
-
Refresh TAMEV-Nano model card and metadata from the measured 896-item audit
Verified signature36da2be
-
Release canonical TAMEV-Nano model weights and SEO model card
Verified signatureec2c8c7