Duplicated from cfahlgren1/enron-autocomplete

cfahlgren1
/

tinynext

Text Generation

fill-in-the-middle

onnxruntime-web

Eval Results (legacy)

Model card Files Files and versions

tinynext / v2 /experiments /tinynext-v2-nofim

128 MB

Ctrl+K

Ctrl+K

1 contributor

History: 1 commit

cfahlgren1's picture

cfahlgren1 HF Staff

tinynext-v2-nofim: 12.5M params, 28 min on GPU

e5dde63 verified about 4 hours ago

metrics
tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago
config.json

312 Bytes
tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago
eval.py

22.4 kB
tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago
eval_set.json

275 kB
tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago
model.onnx

60.8 MB
xet

tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago
model.safetensors

50.2 MB
xet

tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago
model_int8.onnx

15.6 MB
xet

tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago
report.json

24.7 kB
tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago
tokenizer.json

551 kB
tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago
train.py

33.5 kB
tinynext-v2-nofim: 12.5M params, 28 min on GPU about 4 hours ago