sumitdotml
/

moe-emergence

Text Generation

mixture-of-experts

expert-specialization

Model card Files Files and versions

moe-emergence / top2-main-10k

5.45 GB

Ctrl+K

Ctrl+K

2 contributors

History: 8 commits

sumitdotml's picture

Upload top2-main-10k/ckpt-step-9999.pt with huggingface_hub

4fa3232 verified about 2 months ago

best-model.json

818 Bytes
Upload top2-main-10k/best-model.json with huggingface_hub about 2 months ago
best-model.safetensors

1.18 GB
xet

Upload top2-main-10k/best-model.safetensors with huggingface_hub about 2 months ago
ckpt-step-9999.pt

3.08 GB
xet

Upload top2-main-10k/ckpt-step-9999.pt with huggingface_hub about 2 months ago
config.json

560 Bytes
Upload top2-main-10k/config.json with huggingface_hub about 2 months ago
final-model.json

811 Bytes
Upload top2-main-10k/final-model.json with huggingface_hub about 2 months ago
final-model.safetensors

1.18 GB
xet

Upload top2-main-10k/final-model.safetensors with huggingface_hub about 2 months ago
metrics.jsonl

3.49 MB
Upload top2-main-10k/metrics.jsonl with huggingface_hub about 2 months ago
run_summary.json

164 Bytes
Upload top2-main-10k/run_summary.json with huggingface_hub about 2 months ago