jburtoft
/

Trinity-Nano-Neuron-TP1

neuronx-distributed-inference

Mixture of Experts

Model card Files Files and versions

Trinity-Nano-Neuron-TP1

12.3 GB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

jburtoft's picture

Add model card with usage instructions

f14b7fd verified 23 days ago

weights
Trinity-Nano compiled for Neuron TP=1 BS=1 seq_len=2048 (SDK 2.28, pre-sharded weights) 24 days ago
.gitattributes

1.52 kB
initial commit 24 days ago
README.md

6.65 kB
Add model card with usage instructions 23 days ago
model.pt
Detected Pickle imports (16)
- "__torch__.neuronx_distributed.trace.spmd.NxDModelExecutor",
- "__torch__.neuronx_distributed.trace.spmd.NxDModel",
- "torch.jit._pickle.restore_type_tag",
- "__torch__.torch.classes.neuron.LayoutTransformation",
- "torch.jit._pickle.build_intlist",
- "torch.jit._pickle.build_intlist",
- "torch.jit._pickle.build_intlist",
- "torch.jit._pickle.build_intlist",
- "torch.jit._pickle.build_intlist",
- "torch.jit._pickle.build_intlist",
- "torch.jit._pickle.build_intlist",
- "torch.jit._pickle.restore_type_tag",
- "torch._utils._rebuild_tensor_v2",
- "torch.IntStorage",
- "torch.FloatStorage",
- "collections.OrderedDict"
How to fix it?
50.7 MB
xet

Trinity-Nano compiled for Neuron TP=1 BS=1 seq_len=2048 (SDK 2.28, pre-sharded weights) 24 days ago
neuron_config.json

9.52 kB
Trinity-Nano compiled for Neuron TP=1 BS=1 seq_len=2048 (SDK 2.28, pre-sharded weights) 24 days ago