Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
QizhiPei
/
ScaleDiff-7B
like
0
Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
arxiv:
2509.21070
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
refs/pr/1
ScaleDiff-7B
/
all_results.json
QizhiPei
Upload initial model
bee8598
verified
7 months ago
raw
Copy download link
history
blame
Safe
209 Bytes
{
"epoch"
:
3.0
,
"total_flos"
:
2.437260619231934e+21
,
"train_loss"
:
0.21978757351587389
,
"train_runtime"
:
735453.379
,
"train_samples_per_second"
:
2.384
,
"train_steps_per_second"
:
0.074
}