anthonym21
/

Eve-3-SABER-0.5B

Model card Files Files and versions

Eve-3-SABER-0.5B

6 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

anthonym21's picture

Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3

c36dfe4 verified about 2 months ago

.gitattributes

1.52 kB
initial commit about 2 months ago
config.json

882 Bytes
Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3 about 2 months ago
configuration_saber.py

10.6 kB
Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3 about 2 months ago
generation_config.json

152 Bytes
Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3 about 2 months ago
meta.json

122 Bytes
Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3 about 2 months ago
model.safetensors

2 GB
xet

Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3 about 2 months ago
modeling_saber.py

37.3 kB
Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3 about 2 months ago
optimizer.pt
Detected Pickle imports (3)
- "torch._utils._rebuild_tensor_v2",
- "collections.OrderedDict",
- "torch.FloatStorage"
What is a pickle import?
4 GB
xet

Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3 about 2 months ago
tokenizer.json

3.56 MB
Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3 about 2 months ago
tokenizer_config.json

297 Bytes
Step 53110: 27.1B tokens (Stage 2 in progress), loss=1.463, ppl=4.3 about 2 months ago