Duplicated from cfahlgren1/enron-autocomplete

cfahlgren1
/

tinynext

Text Generation

fill-in-the-middle

onnxruntime-web

Eval Results (legacy)

Model card Files Files and versions

404 MB

Ctrl+K

Ctrl+K

1 contributor

History: 11 commits

cfahlgren1's picture

cfahlgren1 HF Staff

tinynext-v2-3b: 12.5M params, 56 min on GPU

dc714b2 verified about 3 hours ago

experiments
tinynext-v2-3b: 12.5M params, 56 min on GPU about 3 hours ago
metrics
v2: 13 MB browser build (int8 download, float compute), export/compress scripts, onnx evals about 5 hours ago
web
v2: 13 MB browser build (int8 download, float compute), export/compress scripts, onnx evals about 5 hours ago
compress.py

5.61 kB
v2: 13 MB browser build (int8 download, float compute), export/compress scripts, onnx evals about 5 hours ago
config.json

312 Bytes
tinynext-v2: 12.5M params, 28 min on GPU about 5 hours ago
eval.py

22.4 kB
v2: 13 MB browser build (int8 download, float compute), export/compress scripts, onnx evals about 5 hours ago
eval_set.json

275 kB
v2: training script, eval harness, eval set and baseline metrics about 7 hours ago
export.py

2.09 kB
export the compressed browser format from train.py instead of int8 activations about 4 hours ago
model.onnx

60.8 MB
xet

tinynext-v2: 12.5M params, 28 min on GPU about 5 hours ago
model.safetensors

50.2 MB
xet

tinynext-v2: 12.5M params, 28 min on GPU about 5 hours ago
model_int8.onnx

23.3 MB
xet

tinynext-v2: 12.5M params, 28 min on GPU about 5 hours ago
report.json

24.5 kB
tinynext-v2: 12.5M params, 28 min on GPU about 5 hours ago
tokenizer.json

551 kB
tinynext-v2: 12.5M params, 28 min on GPU about 5 hours ago
train.py

34.1 kB
export the compressed browser format from train.py instead of int8 activations about 4 hours ago