Tabular Classification
Transformers
Safetensors
felatab
feature-extraction
fela
tabular
in-context-learning
prior-fitted-network
foundation-model
delta-rule
cpu
on-device
custom_code
Eval Results (legacy)
Instructions to use lowdown-labs/fela-tab with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lowdown-labs/fela-tab with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("lowdown-labs/fela-tab", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "metadata": { | |
| "total_size": 1647454116 | |
| }, | |
| "weight_map": { | |
| "blocks.0.attn.b.bias": "model_big.safetensors", | |
| "blocks.0.attn.b.weight": "model_big.safetensors", | |
| "blocks.0.attn.k.weight": "model_big.safetensors", | |
| "blocks.0.attn.o.weight": "model_big.safetensors", | |
| "blocks.0.attn.q.weight": "model_big.safetensors", | |
| "blocks.0.attn.v.weight": "model_big.safetensors", | |
| "blocks.0.ff.0.bias": "model_big.safetensors", | |
| "blocks.0.ff.0.weight": "model_big.safetensors", | |
| "blocks.0.ff.2.bias": "model_big.safetensors", | |
| "blocks.0.ff.2.weight": "model_big.safetensors", | |
| "blocks.0.landmark.gate": "model_big.safetensors", | |
| "blocks.0.landmark.k.weight": "model_big.safetensors", | |
| "blocks.0.landmark.o.weight": "model_big.safetensors", | |
| "blocks.0.landmark.q.weight": "model_big.safetensors", | |
| "blocks.0.landmark.v.weight": "model_big.safetensors", | |
| "blocks.0.n1.bias": "model_big.safetensors", | |
| "blocks.0.n1.weight": "model_big.safetensors", | |
| "blocks.0.n2.bias": "model_big.safetensors", | |
| "blocks.0.n2.weight": "model_big.safetensors", | |
| "blocks.1.attn.b.bias": "model_big.safetensors", | |
| "blocks.1.attn.b.weight": "model_big.safetensors", | |
| "blocks.1.attn.k.weight": "model_big.safetensors", | |
| "blocks.1.attn.o.weight": "model_big.safetensors", | |
| "blocks.1.attn.q.weight": "model_big.safetensors", | |
| "blocks.1.attn.v.weight": "model_big.safetensors", | |
| "blocks.1.ff.0.bias": "model_big.safetensors", | |
| "blocks.1.ff.0.weight": "model_big.safetensors", | |
| "blocks.1.ff.2.bias": "model_big.safetensors", | |
| "blocks.1.ff.2.weight": "model_big.safetensors", | |
| "blocks.1.landmark.gate": "model_big.safetensors", | |
| "blocks.1.landmark.k.weight": "model_big.safetensors", | |
| "blocks.1.landmark.o.weight": "model_big.safetensors", | |
| "blocks.1.landmark.q.weight": "model_big.safetensors", | |
| "blocks.1.landmark.v.weight": "model_big.safetensors", | |
| "blocks.1.n1.bias": "model_big.safetensors", | |
| "blocks.1.n1.weight": "model_big.safetensors", | |
| "blocks.1.n2.bias": "model_big.safetensors", | |
| "blocks.1.n2.weight": "model_big.safetensors", | |
| "blocks.10.attn.b.bias": "model_big.safetensors", | |
| "blocks.10.attn.b.weight": "model_big.safetensors", | |
| "blocks.10.attn.k.weight": "model_big.safetensors", | |
| "blocks.10.attn.o.weight": "model_big.safetensors", | |
| "blocks.10.attn.q.weight": "model_big.safetensors", | |
| "blocks.10.attn.v.weight": "model_big.safetensors", | |
| "blocks.10.ff.0.bias": "model_big.safetensors", | |
| "blocks.10.ff.0.weight": "model_big.safetensors", | |
| "blocks.10.ff.2.bias": "model_big.safetensors", | |
| "blocks.10.ff.2.weight": "model_big.safetensors", | |
| "blocks.10.landmark.gate": "model_big.safetensors", | |
| "blocks.10.landmark.k.weight": "model_big.safetensors", | |
| "blocks.10.landmark.o.weight": "model_big.safetensors", | |
| "blocks.10.landmark.q.weight": "model_big.safetensors", | |
| "blocks.10.landmark.v.weight": "model_big.safetensors", | |
| "blocks.10.n1.bias": "model_big.safetensors", | |
| "blocks.10.n1.weight": "model_big.safetensors", | |
| "blocks.10.n2.bias": "model_big.safetensors", | |
| "blocks.10.n2.weight": "model_big.safetensors", | |
| "blocks.11.attn.b.bias": "model_big.safetensors", | |
| "blocks.11.attn.b.weight": "model_big.safetensors", | |
| "blocks.11.attn.k.weight": "model_big.safetensors", | |
| "blocks.11.attn.o.weight": "model_big.safetensors", | |
| "blocks.11.attn.q.weight": "model_big.safetensors", | |
| "blocks.11.attn.v.weight": "model_big.safetensors", | |
| "blocks.11.ff.0.bias": "model_big.safetensors", | |
| "blocks.11.ff.0.weight": "model_big.safetensors", | |
| "blocks.11.ff.2.bias": "model_big.safetensors", | |
| "blocks.11.ff.2.weight": "model_big.safetensors", | |
| "blocks.11.landmark.gate": "model_big.safetensors", | |
| "blocks.11.landmark.k.weight": "model_big.safetensors", | |
| "blocks.11.landmark.o.weight": "model_big.safetensors", | |
| "blocks.11.landmark.q.weight": "model_big.safetensors", | |
| "blocks.11.landmark.v.weight": "model_big.safetensors", | |
| "blocks.11.n1.bias": "model_big.safetensors", | |
| "blocks.11.n1.weight": "model_big.safetensors", | |
| "blocks.11.n2.bias": "model_big.safetensors", | |
| "blocks.11.n2.weight": "model_big.safetensors", | |
| "blocks.12.attn.b.bias": "model_big.safetensors", | |
| "blocks.12.attn.b.weight": "model_big.safetensors", | |
| "blocks.12.attn.k.weight": "model_big.safetensors", | |
| "blocks.12.attn.o.weight": "model_big.safetensors", | |
| "blocks.12.attn.q.weight": "model_big.safetensors", | |
| "blocks.12.attn.v.weight": "model_big.safetensors", | |
| "blocks.12.ff.0.bias": "model_big.safetensors", | |
| "blocks.12.ff.0.weight": "model_big.safetensors", | |
| "blocks.12.ff.2.bias": "model_big.safetensors", | |
| "blocks.12.ff.2.weight": "model_big.safetensors", | |
| "blocks.12.landmark.gate": "model_big.safetensors", | |
| "blocks.12.landmark.k.weight": "model_big.safetensors", | |
| "blocks.12.landmark.o.weight": "model_big.safetensors", | |
| "blocks.12.landmark.q.weight": "model_big.safetensors", | |
| "blocks.12.landmark.v.weight": "model_big.safetensors", | |
| "blocks.12.n1.bias": "model_big.safetensors", | |
| "blocks.12.n1.weight": "model_big.safetensors", | |
| "blocks.12.n2.bias": "model_big.safetensors", | |
| "blocks.12.n2.weight": "model_big.safetensors", | |
| "blocks.13.attn.b.bias": "model_big.safetensors", | |
| "blocks.13.attn.b.weight": "model_big.safetensors", | |
| "blocks.13.attn.k.weight": "model_big.safetensors", | |
| "blocks.13.attn.o.weight": "model_big.safetensors", | |
| "blocks.13.attn.q.weight": "model_big.safetensors", | |
| "blocks.13.attn.v.weight": "model_big.safetensors", | |
| "blocks.13.ff.0.bias": "model_big.safetensors", | |
| "blocks.13.ff.0.weight": "model_big.safetensors", | |
| "blocks.13.ff.2.bias": "model_big.safetensors", | |
| "blocks.13.ff.2.weight": "model_big.safetensors", | |
| "blocks.13.landmark.gate": "model_big.safetensors", | |
| "blocks.13.landmark.k.weight": "model_big.safetensors", | |
| "blocks.13.landmark.o.weight": "model_big.safetensors", | |
| "blocks.13.landmark.q.weight": "model_big.safetensors", | |
| "blocks.13.landmark.v.weight": "model_big.safetensors", | |
| "blocks.13.n1.bias": "model_big.safetensors", | |
| "blocks.13.n1.weight": "model_big.safetensors", | |
| "blocks.13.n2.bias": "model_big.safetensors", | |
| "blocks.13.n2.weight": "model_big.safetensors", | |
| "blocks.14.attn.b.bias": "model_big.safetensors", | |
| "blocks.14.attn.b.weight": "model_big.safetensors", | |
| "blocks.14.attn.k.weight": "model_big.safetensors", | |
| "blocks.14.attn.o.weight": "model_big.safetensors", | |
| "blocks.14.attn.q.weight": "model_big.safetensors", | |
| "blocks.14.attn.v.weight": "model_big.safetensors", | |
| "blocks.14.ff.0.bias": "model_big.safetensors", | |
| "blocks.14.ff.0.weight": "model_big.safetensors", | |
| "blocks.14.ff.2.bias": "model_big.safetensors", | |
| "blocks.14.ff.2.weight": "model_big.safetensors", | |
| "blocks.14.landmark.gate": "model_big.safetensors", | |
| "blocks.14.landmark.k.weight": "model_big.safetensors", | |
| "blocks.14.landmark.o.weight": "model_big.safetensors", | |
| "blocks.14.landmark.q.weight": "model_big.safetensors", | |
| "blocks.14.landmark.v.weight": "model_big.safetensors", | |
| "blocks.14.n1.bias": "model_big.safetensors", | |
| "blocks.14.n1.weight": "model_big.safetensors", | |
| "blocks.14.n2.bias": "model_big.safetensors", | |
| "blocks.14.n2.weight": "model_big.safetensors", | |
| "blocks.15.attn.b.bias": "model_big.safetensors", | |
| "blocks.15.attn.b.weight": "model_big.safetensors", | |
| "blocks.15.attn.k.weight": "model_big.safetensors", | |
| "blocks.15.attn.o.weight": "model_big.safetensors", | |
| "blocks.15.attn.q.weight": "model_big.safetensors", | |
| "blocks.15.attn.v.weight": "model_big.safetensors", | |
| "blocks.15.ff.0.bias": "model_big.safetensors", | |
| "blocks.15.ff.0.weight": "model_big.safetensors", | |
| "blocks.15.ff.2.bias": "model_big.safetensors", | |
| "blocks.15.ff.2.weight": "model_big.safetensors", | |
| "blocks.15.landmark.gate": "model_big.safetensors", | |
| "blocks.15.landmark.k.weight": "model_big.safetensors", | |
| "blocks.15.landmark.o.weight": "model_big.safetensors", | |
| "blocks.15.landmark.q.weight": "model_big.safetensors", | |
| "blocks.15.landmark.v.weight": "model_big.safetensors", | |
| "blocks.15.n1.bias": "model_big.safetensors", | |
| "blocks.15.n1.weight": "model_big.safetensors", | |
| "blocks.15.n2.bias": "model_big.safetensors", | |
| "blocks.15.n2.weight": "model_big.safetensors", | |
| "blocks.16.attn.b.bias": "model_big.safetensors", | |
| "blocks.16.attn.b.weight": "model_big.safetensors", | |
| "blocks.16.attn.k.weight": "model_big.safetensors", | |
| "blocks.16.attn.o.weight": "model_big.safetensors", | |
| "blocks.16.attn.q.weight": "model_big.safetensors", | |
| "blocks.16.attn.v.weight": "model_big.safetensors", | |
| "blocks.16.ff.0.bias": "model_big.safetensors", | |
| "blocks.16.ff.0.weight": "model_big.safetensors", | |
| "blocks.16.ff.2.bias": "model_big.safetensors", | |
| "blocks.16.ff.2.weight": "model_big.safetensors", | |
| "blocks.16.landmark.gate": "model_big.safetensors", | |
| "blocks.16.landmark.k.weight": "model_big.safetensors", | |
| "blocks.16.landmark.o.weight": "model_big.safetensors", | |
| "blocks.16.landmark.q.weight": "model_big.safetensors", | |
| "blocks.16.landmark.v.weight": "model_big.safetensors", | |
| "blocks.16.n1.bias": "model_big.safetensors", | |
| "blocks.16.n1.weight": "model_big.safetensors", | |
| "blocks.16.n2.bias": "model_big.safetensors", | |
| "blocks.16.n2.weight": "model_big.safetensors", | |
| "blocks.17.attn.b.bias": "model_big.safetensors", | |
| "blocks.17.attn.b.weight": "model_big.safetensors", | |
| "blocks.17.attn.k.weight": "model_big.safetensors", | |
| "blocks.17.attn.o.weight": "model_big.safetensors", | |
| "blocks.17.attn.q.weight": "model_big.safetensors", | |
| "blocks.17.attn.v.weight": "model_big.safetensors", | |
| "blocks.17.ff.0.bias": "model_big.safetensors", | |
| "blocks.17.ff.0.weight": "model_big.safetensors", | |
| "blocks.17.ff.2.bias": "model_big.safetensors", | |
| "blocks.17.ff.2.weight": "model_big.safetensors", | |
| "blocks.17.landmark.gate": "model_big.safetensors", | |
| "blocks.17.landmark.k.weight": "model_big.safetensors", | |
| "blocks.17.landmark.o.weight": "model_big.safetensors", | |
| "blocks.17.landmark.q.weight": "model_big.safetensors", | |
| "blocks.17.landmark.v.weight": "model_big.safetensors", | |
| "blocks.17.n1.bias": "model_big.safetensors", | |
| "blocks.17.n1.weight": "model_big.safetensors", | |
| "blocks.17.n2.bias": "model_big.safetensors", | |
| "blocks.17.n2.weight": "model_big.safetensors", | |
| "blocks.18.attn.b.bias": "model_big.safetensors", | |
| "blocks.18.attn.b.weight": "model_big.safetensors", | |
| "blocks.18.attn.k.weight": "model_big.safetensors", | |
| "blocks.18.attn.o.weight": "model_big.safetensors", | |
| "blocks.18.attn.q.weight": "model_big.safetensors", | |
| "blocks.18.attn.v.weight": "model_big.safetensors", | |
| "blocks.18.ff.0.bias": "model_big.safetensors", | |
| "blocks.18.ff.0.weight": "model_big.safetensors", | |
| "blocks.18.ff.2.bias": "model_big.safetensors", | |
| "blocks.18.ff.2.weight": "model_big.safetensors", | |
| "blocks.18.landmark.gate": "model_big.safetensors", | |
| "blocks.18.landmark.k.weight": "model_big.safetensors", | |
| "blocks.18.landmark.o.weight": "model_big.safetensors", | |
| "blocks.18.landmark.q.weight": "model_big.safetensors", | |
| "blocks.18.landmark.v.weight": "model_big.safetensors", | |
| "blocks.18.n1.bias": "model_big.safetensors", | |
| "blocks.18.n1.weight": "model_big.safetensors", | |
| "blocks.18.n2.bias": "model_big.safetensors", | |
| "blocks.18.n2.weight": "model_big.safetensors", | |
| "blocks.19.attn.b.bias": "model_big.safetensors", | |
| "blocks.19.attn.b.weight": "model_big.safetensors", | |
| "blocks.19.attn.k.weight": "model_big.safetensors", | |
| "blocks.19.attn.o.weight": "model_big.safetensors", | |
| "blocks.19.attn.q.weight": "model_big.safetensors", | |
| "blocks.19.attn.v.weight": "model_big.safetensors", | |
| "blocks.19.ff.0.bias": "model_big.safetensors", | |
| "blocks.19.ff.0.weight": "model_big.safetensors", | |
| "blocks.19.ff.2.bias": "model_big.safetensors", | |
| "blocks.19.ff.2.weight": "model_big.safetensors", | |
| "blocks.19.landmark.gate": "model_big.safetensors", | |
| "blocks.19.landmark.k.weight": "model_big.safetensors", | |
| "blocks.19.landmark.o.weight": "model_big.safetensors", | |
| "blocks.19.landmark.q.weight": "model_big.safetensors", | |
| "blocks.19.landmark.v.weight": "model_big.safetensors", | |
| "blocks.19.n1.bias": "model_big.safetensors", | |
| "blocks.19.n1.weight": "model_big.safetensors", | |
| "blocks.19.n2.bias": "model_big.safetensors", | |
| "blocks.19.n2.weight": "model_big.safetensors", | |
| "blocks.2.attn.b.bias": "model_big.safetensors", | |
| "blocks.2.attn.b.weight": "model_big.safetensors", | |
| "blocks.2.attn.k.weight": "model_big.safetensors", | |
| "blocks.2.attn.o.weight": "model_big.safetensors", | |
| "blocks.2.attn.q.weight": "model_big.safetensors", | |
| "blocks.2.attn.v.weight": "model_big.safetensors", | |
| "blocks.2.ff.0.bias": "model_big.safetensors", | |
| "blocks.2.ff.0.weight": "model_big.safetensors", | |
| "blocks.2.ff.2.bias": "model_big.safetensors", | |
| "blocks.2.ff.2.weight": "model_big.safetensors", | |
| "blocks.2.landmark.gate": "model_big.safetensors", | |
| "blocks.2.landmark.k.weight": "model_big.safetensors", | |
| "blocks.2.landmark.o.weight": "model_big.safetensors", | |
| "blocks.2.landmark.q.weight": "model_big.safetensors", | |
| "blocks.2.landmark.v.weight": "model_big.safetensors", | |
| "blocks.2.n1.bias": "model_big.safetensors", | |
| "blocks.2.n1.weight": "model_big.safetensors", | |
| "blocks.2.n2.bias": "model_big.safetensors", | |
| "blocks.2.n2.weight": "model_big.safetensors", | |
| "blocks.20.attn.b.bias": "model_big.safetensors", | |
| "blocks.20.attn.b.weight": "model_big.safetensors", | |
| "blocks.20.attn.k.weight": "model_big.safetensors", | |
| "blocks.20.attn.o.weight": "model_big.safetensors", | |
| "blocks.20.attn.q.weight": "model_big.safetensors", | |
| "blocks.20.attn.v.weight": "model_big.safetensors", | |
| "blocks.20.ff.0.bias": "model_big.safetensors", | |
| "blocks.20.ff.0.weight": "model_big.safetensors", | |
| "blocks.20.ff.2.bias": "model_big.safetensors", | |
| "blocks.20.ff.2.weight": "model_big.safetensors", | |
| "blocks.20.landmark.gate": "model_big.safetensors", | |
| "blocks.20.landmark.k.weight": "model_big.safetensors", | |
| "blocks.20.landmark.o.weight": "model_big.safetensors", | |
| "blocks.20.landmark.q.weight": "model_big.safetensors", | |
| "blocks.20.landmark.v.weight": "model_big.safetensors", | |
| "blocks.20.n1.bias": "model_big.safetensors", | |
| "blocks.20.n1.weight": "model_big.safetensors", | |
| "blocks.20.n2.bias": "model_big.safetensors", | |
| "blocks.20.n2.weight": "model_big.safetensors", | |
| "blocks.21.attn.b.bias": "model_big.safetensors", | |
| "blocks.21.attn.b.weight": "model_big.safetensors", | |
| "blocks.21.attn.k.weight": "model_big.safetensors", | |
| "blocks.21.attn.o.weight": "model_big.safetensors", | |
| "blocks.21.attn.q.weight": "model_big.safetensors", | |
| "blocks.21.attn.v.weight": "model_big.safetensors", | |
| "blocks.21.ff.0.bias": "model_big.safetensors", | |
| "blocks.21.ff.0.weight": "model_big.safetensors", | |
| "blocks.21.ff.2.bias": "model_big.safetensors", | |
| "blocks.21.ff.2.weight": "model_big.safetensors", | |
| "blocks.21.landmark.gate": "model_big.safetensors", | |
| "blocks.21.landmark.k.weight": "model_big.safetensors", | |
| "blocks.21.landmark.o.weight": "model_big.safetensors", | |
| "blocks.21.landmark.q.weight": "model_big.safetensors", | |
| "blocks.21.landmark.v.weight": "model_big.safetensors", | |
| "blocks.21.n1.bias": "model_big.safetensors", | |
| "blocks.21.n1.weight": "model_big.safetensors", | |
| "blocks.21.n2.bias": "model_big.safetensors", | |
| "blocks.21.n2.weight": "model_big.safetensors", | |
| "blocks.22.attn.b.bias": "model_big.safetensors", | |
| "blocks.22.attn.b.weight": "model_big.safetensors", | |
| "blocks.22.attn.k.weight": "model_big.safetensors", | |
| "blocks.22.attn.o.weight": "model_big.safetensors", | |
| "blocks.22.attn.q.weight": "model_big.safetensors", | |
| "blocks.22.attn.v.weight": "model_big.safetensors", | |
| "blocks.22.ff.0.bias": "model_big.safetensors", | |
| "blocks.22.ff.0.weight": "model_big.safetensors", | |
| "blocks.22.ff.2.bias": "model_big.safetensors", | |
| "blocks.22.ff.2.weight": "model_big.safetensors", | |
| "blocks.22.landmark.gate": "model_big.safetensors", | |
| "blocks.22.landmark.k.weight": "model_big.safetensors", | |
| "blocks.22.landmark.o.weight": "model_big.safetensors", | |
| "blocks.22.landmark.q.weight": "model_big.safetensors", | |
| "blocks.22.landmark.v.weight": "model_big.safetensors", | |
| "blocks.22.n1.bias": "model_big.safetensors", | |
| "blocks.22.n1.weight": "model_big.safetensors", | |
| "blocks.22.n2.bias": "model_big.safetensors", | |
| "blocks.22.n2.weight": "model_big.safetensors", | |
| "blocks.23.attn.b.bias": "model_big.safetensors", | |
| "blocks.23.attn.b.weight": "model_big.safetensors", | |
| "blocks.23.attn.k.weight": "model_big.safetensors", | |
| "blocks.23.attn.o.weight": "model_big.safetensors", | |
| "blocks.23.attn.q.weight": "model_big.safetensors", | |
| "blocks.23.attn.v.weight": "model_big.safetensors", | |
| "blocks.23.ff.0.bias": "model_big.safetensors", | |
| "blocks.23.ff.0.weight": "model_big.safetensors", | |
| "blocks.23.ff.2.bias": "model_big.safetensors", | |
| "blocks.23.ff.2.weight": "model_big.safetensors", | |
| "blocks.23.landmark.gate": "model_big.safetensors", | |
| "blocks.23.landmark.k.weight": "model_big.safetensors", | |
| "blocks.23.landmark.o.weight": "model_big.safetensors", | |
| "blocks.23.landmark.q.weight": "model_big.safetensors", | |
| "blocks.23.landmark.v.weight": "model_big.safetensors", | |
| "blocks.23.n1.bias": "model_big.safetensors", | |
| "blocks.23.n1.weight": "model_big.safetensors", | |
| "blocks.23.n2.bias": "model_big.safetensors", | |
| "blocks.23.n2.weight": "model_big.safetensors", | |
| "blocks.24.attn.b.bias": "model_big.safetensors", | |
| "blocks.24.attn.b.weight": "model_big.safetensors", | |
| "blocks.24.attn.k.weight": "model_big.safetensors", | |
| "blocks.24.attn.o.weight": "model_big.safetensors", | |
| "blocks.24.attn.q.weight": "model_big.safetensors", | |
| "blocks.24.attn.v.weight": "model_big.safetensors", | |
| "blocks.24.ff.0.bias": "model_big.safetensors", | |
| "blocks.24.ff.0.weight": "model_big.safetensors", | |
| "blocks.24.ff.2.bias": "model_big.safetensors", | |
| "blocks.24.ff.2.weight": "model_big.safetensors", | |
| "blocks.24.landmark.gate": "model_big.safetensors", | |
| "blocks.24.landmark.k.weight": "model_big.safetensors", | |
| "blocks.24.landmark.o.weight": "model_big.safetensors", | |
| "blocks.24.landmark.q.weight": "model_big.safetensors", | |
| "blocks.24.landmark.v.weight": "model_big.safetensors", | |
| "blocks.24.n1.bias": "model_big.safetensors", | |
| "blocks.24.n1.weight": "model_big.safetensors", | |
| "blocks.24.n2.bias": "model_big.safetensors", | |
| "blocks.24.n2.weight": "model_big.safetensors", | |
| "blocks.25.attn.b.bias": "model_big.safetensors", | |
| "blocks.25.attn.b.weight": "model_big.safetensors", | |
| "blocks.25.attn.k.weight": "model_big.safetensors", | |
| "blocks.25.attn.o.weight": "model_big.safetensors", | |
| "blocks.25.attn.q.weight": "model_big.safetensors", | |
| "blocks.25.attn.v.weight": "model_big.safetensors", | |
| "blocks.25.ff.0.bias": "model_big.safetensors", | |
| "blocks.25.ff.0.weight": "model_big.safetensors", | |
| "blocks.25.ff.2.bias": "model_big.safetensors", | |
| "blocks.25.ff.2.weight": "model_big.safetensors", | |
| "blocks.25.landmark.gate": "model_big.safetensors", | |
| "blocks.25.landmark.k.weight": "model_big.safetensors", | |
| "blocks.25.landmark.o.weight": "model_big.safetensors", | |
| "blocks.25.landmark.q.weight": "model_big.safetensors", | |
| "blocks.25.landmark.v.weight": "model_big.safetensors", | |
| "blocks.25.n1.bias": "model_big.safetensors", | |
| "blocks.25.n1.weight": "model_big.safetensors", | |
| "blocks.25.n2.bias": "model_big.safetensors", | |
| "blocks.25.n2.weight": "model_big.safetensors", | |
| "blocks.26.attn.b.bias": "model_big.safetensors", | |
| "blocks.26.attn.b.weight": "model_big.safetensors", | |
| "blocks.26.attn.k.weight": "model_big.safetensors", | |
| "blocks.26.attn.o.weight": "model_big.safetensors", | |
| "blocks.26.attn.q.weight": "model_big.safetensors", | |
| "blocks.26.attn.v.weight": "model_big.safetensors", | |
| "blocks.26.ff.0.bias": "model_big.safetensors", | |
| "blocks.26.ff.0.weight": "model_big.safetensors", | |
| "blocks.26.ff.2.bias": "model_big.safetensors", | |
| "blocks.26.ff.2.weight": "model_big.safetensors", | |
| "blocks.26.landmark.gate": "model_big.safetensors", | |
| "blocks.26.landmark.k.weight": "model_big.safetensors", | |
| "blocks.26.landmark.o.weight": "model_big.safetensors", | |
| "blocks.26.landmark.q.weight": "model_big.safetensors", | |
| "blocks.26.landmark.v.weight": "model_big.safetensors", | |
| "blocks.26.n1.bias": "model_big.safetensors", | |
| "blocks.26.n1.weight": "model_big.safetensors", | |
| "blocks.26.n2.bias": "model_big.safetensors", | |
| "blocks.26.n2.weight": "model_big.safetensors", | |
| "blocks.27.attn.b.bias": "model_big.safetensors", | |
| "blocks.27.attn.b.weight": "model_big.safetensors", | |
| "blocks.27.attn.k.weight": "model_big.safetensors", | |
| "blocks.27.attn.o.weight": "model_big.safetensors", | |
| "blocks.27.attn.q.weight": "model_big.safetensors", | |
| "blocks.27.attn.v.weight": "model_big.safetensors", | |
| "blocks.27.ff.0.bias": "model_big.safetensors", | |
| "blocks.27.ff.0.weight": "model_big.safetensors", | |
| "blocks.27.ff.2.bias": "model_big.safetensors", | |
| "blocks.27.ff.2.weight": "model_big.safetensors", | |
| "blocks.27.landmark.gate": "model_big.safetensors", | |
| "blocks.27.landmark.k.weight": "model_big.safetensors", | |
| "blocks.27.landmark.o.weight": "model_big.safetensors", | |
| "blocks.27.landmark.q.weight": "model_big.safetensors", | |
| "blocks.27.landmark.v.weight": "model_big.safetensors", | |
| "blocks.27.n1.bias": "model_big.safetensors", | |
| "blocks.27.n1.weight": "model_big.safetensors", | |
| "blocks.27.n2.bias": "model_big.safetensors", | |
| "blocks.27.n2.weight": "model_big.safetensors", | |
| "blocks.3.attn.b.bias": "model_big.safetensors", | |
| "blocks.3.attn.b.weight": "model_big.safetensors", | |
| "blocks.3.attn.k.weight": "model_big.safetensors", | |
| "blocks.3.attn.o.weight": "model_big.safetensors", | |
| "blocks.3.attn.q.weight": "model_big.safetensors", | |
| "blocks.3.attn.v.weight": "model_big.safetensors", | |
| "blocks.3.ff.0.bias": "model_big.safetensors", | |
| "blocks.3.ff.0.weight": "model_big.safetensors", | |
| "blocks.3.ff.2.bias": "model_big.safetensors", | |
| "blocks.3.ff.2.weight": "model_big.safetensors", | |
| "blocks.3.landmark.gate": "model_big.safetensors", | |
| "blocks.3.landmark.k.weight": "model_big.safetensors", | |
| "blocks.3.landmark.o.weight": "model_big.safetensors", | |
| "blocks.3.landmark.q.weight": "model_big.safetensors", | |
| "blocks.3.landmark.v.weight": "model_big.safetensors", | |
| "blocks.3.n1.bias": "model_big.safetensors", | |
| "blocks.3.n1.weight": "model_big.safetensors", | |
| "blocks.3.n2.bias": "model_big.safetensors", | |
| "blocks.3.n2.weight": "model_big.safetensors", | |
| "blocks.4.attn.b.bias": "model_big.safetensors", | |
| "blocks.4.attn.b.weight": "model_big.safetensors", | |
| "blocks.4.attn.k.weight": "model_big.safetensors", | |
| "blocks.4.attn.o.weight": "model_big.safetensors", | |
| "blocks.4.attn.q.weight": "model_big.safetensors", | |
| "blocks.4.attn.v.weight": "model_big.safetensors", | |
| "blocks.4.ff.0.bias": "model_big.safetensors", | |
| "blocks.4.ff.0.weight": "model_big.safetensors", | |
| "blocks.4.ff.2.bias": "model_big.safetensors", | |
| "blocks.4.ff.2.weight": "model_big.safetensors", | |
| "blocks.4.landmark.gate": "model_big.safetensors", | |
| "blocks.4.landmark.k.weight": "model_big.safetensors", | |
| "blocks.4.landmark.o.weight": "model_big.safetensors", | |
| "blocks.4.landmark.q.weight": "model_big.safetensors", | |
| "blocks.4.landmark.v.weight": "model_big.safetensors", | |
| "blocks.4.n1.bias": "model_big.safetensors", | |
| "blocks.4.n1.weight": "model_big.safetensors", | |
| "blocks.4.n2.bias": "model_big.safetensors", | |
| "blocks.4.n2.weight": "model_big.safetensors", | |
| "blocks.5.attn.b.bias": "model_big.safetensors", | |
| "blocks.5.attn.b.weight": "model_big.safetensors", | |
| "blocks.5.attn.k.weight": "model_big.safetensors", | |
| "blocks.5.attn.o.weight": "model_big.safetensors", | |
| "blocks.5.attn.q.weight": "model_big.safetensors", | |
| "blocks.5.attn.v.weight": "model_big.safetensors", | |
| "blocks.5.ff.0.bias": "model_big.safetensors", | |
| "blocks.5.ff.0.weight": "model_big.safetensors", | |
| "blocks.5.ff.2.bias": "model_big.safetensors", | |
| "blocks.5.ff.2.weight": "model_big.safetensors", | |
| "blocks.5.landmark.gate": "model_big.safetensors", | |
| "blocks.5.landmark.k.weight": "model_big.safetensors", | |
| "blocks.5.landmark.o.weight": "model_big.safetensors", | |
| "blocks.5.landmark.q.weight": "model_big.safetensors", | |
| "blocks.5.landmark.v.weight": "model_big.safetensors", | |
| "blocks.5.n1.bias": "model_big.safetensors", | |
| "blocks.5.n1.weight": "model_big.safetensors", | |
| "blocks.5.n2.bias": "model_big.safetensors", | |
| "blocks.5.n2.weight": "model_big.safetensors", | |
| "blocks.6.attn.b.bias": "model_big.safetensors", | |
| "blocks.6.attn.b.weight": "model_big.safetensors", | |
| "blocks.6.attn.k.weight": "model_big.safetensors", | |
| "blocks.6.attn.o.weight": "model_big.safetensors", | |
| "blocks.6.attn.q.weight": "model_big.safetensors", | |
| "blocks.6.attn.v.weight": "model_big.safetensors", | |
| "blocks.6.ff.0.bias": "model_big.safetensors", | |
| "blocks.6.ff.0.weight": "model_big.safetensors", | |
| "blocks.6.ff.2.bias": "model_big.safetensors", | |
| "blocks.6.ff.2.weight": "model_big.safetensors", | |
| "blocks.6.landmark.gate": "model_big.safetensors", | |
| "blocks.6.landmark.k.weight": "model_big.safetensors", | |
| "blocks.6.landmark.o.weight": "model_big.safetensors", | |
| "blocks.6.landmark.q.weight": "model_big.safetensors", | |
| "blocks.6.landmark.v.weight": "model_big.safetensors", | |
| "blocks.6.n1.bias": "model_big.safetensors", | |
| "blocks.6.n1.weight": "model_big.safetensors", | |
| "blocks.6.n2.bias": "model_big.safetensors", | |
| "blocks.6.n2.weight": "model_big.safetensors", | |
| "blocks.7.attn.b.bias": "model_big.safetensors", | |
| "blocks.7.attn.b.weight": "model_big.safetensors", | |
| "blocks.7.attn.k.weight": "model_big.safetensors", | |
| "blocks.7.attn.o.weight": "model_big.safetensors", | |
| "blocks.7.attn.q.weight": "model_big.safetensors", | |
| "blocks.7.attn.v.weight": "model_big.safetensors", | |
| "blocks.7.ff.0.bias": "model_big.safetensors", | |
| "blocks.7.ff.0.weight": "model_big.safetensors", | |
| "blocks.7.ff.2.bias": "model_big.safetensors", | |
| "blocks.7.ff.2.weight": "model_big.safetensors", | |
| "blocks.7.landmark.gate": "model_big.safetensors", | |
| "blocks.7.landmark.k.weight": "model_big.safetensors", | |
| "blocks.7.landmark.o.weight": "model_big.safetensors", | |
| "blocks.7.landmark.q.weight": "model_big.safetensors", | |
| "blocks.7.landmark.v.weight": "model_big.safetensors", | |
| "blocks.7.n1.bias": "model_big.safetensors", | |
| "blocks.7.n1.weight": "model_big.safetensors", | |
| "blocks.7.n2.bias": "model_big.safetensors", | |
| "blocks.7.n2.weight": "model_big.safetensors", | |
| "blocks.8.attn.b.bias": "model_big.safetensors", | |
| "blocks.8.attn.b.weight": "model_big.safetensors", | |
| "blocks.8.attn.k.weight": "model_big.safetensors", | |
| "blocks.8.attn.o.weight": "model_big.safetensors", | |
| "blocks.8.attn.q.weight": "model_big.safetensors", | |
| "blocks.8.attn.v.weight": "model_big.safetensors", | |
| "blocks.8.ff.0.bias": "model_big.safetensors", | |
| "blocks.8.ff.0.weight": "model_big.safetensors", | |
| "blocks.8.ff.2.bias": "model_big.safetensors", | |
| "blocks.8.ff.2.weight": "model_big.safetensors", | |
| "blocks.8.landmark.gate": "model_big.safetensors", | |
| "blocks.8.landmark.k.weight": "model_big.safetensors", | |
| "blocks.8.landmark.o.weight": "model_big.safetensors", | |
| "blocks.8.landmark.q.weight": "model_big.safetensors", | |
| "blocks.8.landmark.v.weight": "model_big.safetensors", | |
| "blocks.8.n1.bias": "model_big.safetensors", | |
| "blocks.8.n1.weight": "model_big.safetensors", | |
| "blocks.8.n2.bias": "model_big.safetensors", | |
| "blocks.8.n2.weight": "model_big.safetensors", | |
| "blocks.9.attn.b.bias": "model_big.safetensors", | |
| "blocks.9.attn.b.weight": "model_big.safetensors", | |
| "blocks.9.attn.k.weight": "model_big.safetensors", | |
| "blocks.9.attn.o.weight": "model_big.safetensors", | |
| "blocks.9.attn.q.weight": "model_big.safetensors", | |
| "blocks.9.attn.v.weight": "model_big.safetensors", | |
| "blocks.9.ff.0.bias": "model_big.safetensors", | |
| "blocks.9.ff.0.weight": "model_big.safetensors", | |
| "blocks.9.ff.2.bias": "model_big.safetensors", | |
| "blocks.9.ff.2.weight": "model_big.safetensors", | |
| "blocks.9.landmark.gate": "model_big.safetensors", | |
| "blocks.9.landmark.k.weight": "model_big.safetensors", | |
| "blocks.9.landmark.o.weight": "model_big.safetensors", | |
| "blocks.9.landmark.q.weight": "model_big.safetensors", | |
| "blocks.9.landmark.v.weight": "model_big.safetensors", | |
| "blocks.9.n1.bias": "model_big.safetensors", | |
| "blocks.9.n1.weight": "model_big.safetensors", | |
| "blocks.9.n2.bias": "model_big.safetensors", | |
| "blocks.9.n2.weight": "model_big.safetensors", | |
| "cls_head.bias": "model_big.safetensors", | |
| "cls_head.weight": "model_big.safetensors", | |
| "cls_label_emb.weight": "model_big.safetensors", | |
| "feat_enc.bias": "model_big.safetensors", | |
| "feat_enc.weight": "model_big.safetensors", | |
| "norm.bias": "model_big.safetensors", | |
| "norm.weight": "model_big.safetensors", | |
| "reg_head.bias": "model_big.safetensors", | |
| "reg_head.weight": "model_big.safetensors", | |
| "reg_label.bias": "model_big.safetensors", | |
| "reg_label.weight": "model_big.safetensors", | |
| "reg_label_gate": "model_big.safetensors", | |
| "type_emb.weight": "model_big.safetensors" | |
| } | |
| } |