Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
lightblue
/
DeepSeek-R1-Distill-Qwen-7B-Japanese
like
25
Follow
Lightblue KK.
99
Text Generation
Transformers
Safetensors
lightblue/distilabel-reasoning-R1-Llama-70B
Japanese
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
b3ee0d4
DeepSeek-R1-Distill-Qwen-7B-Japanese
/
eval_results.json
ptrdvn
Upload folder using huggingface_hub
b3ee0d4
verified
23 days ago
raw
Copy download link
history
blame
Safe
158 Bytes
{
"epoch"
:
1.0
,
"eval_loss"
:
0.4519386291503906
,
"eval_runtime"
:
0.8439
,
"eval_samples_per_second"
:
4.74
,
"eval_steps_per_second"
:
1.185
}