Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Posts
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

agentica-org
/
DeepScaleR-1.5B-Preview

Text Generation
Transformers
Safetensors
English
qwen2
text-generation-inference
Model card Files Files and versions Community
19
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Possible version of this model that will support Tool-integrated Reasoning (TIR)?

2
#19 opened 2 months ago by
nvhf

Non- Math Use Cases?

1
3
#18 opened 3 months ago by
DeFactOfficial

Other languages than English not well supported

1
#17 opened 3 months ago by
scientist082

Genuinely Impressive Little Model!

2
2
#16 opened 3 months ago by
SytanSD

Why use a small model like the 1.5B? Instead of a larger one? Is there a reason?

4
#15 opened 3 months ago by
likewendy

Can we run this on CPU?

1
#14 opened 3 months ago by
Amarjitkr

I have difficulty to trigger thinking process

3
#12 opened 3 months ago by
shing3232

GGUF Quantizations

1
#11 opened 3 months ago by
Garydesu

How to use it? Can I have a conversation?

1
#10 opened 3 months ago by
viaho

0.5B Model

2
1
#9 opened 3 months ago by
chrisvnz

Efficient Fine-Tuning of DeepScaleR-1.5B Without Increasing Parameters

4
#8 opened 3 months ago by
HassanStar

Larger models?

5
1
#7 opened 3 months ago by
DonGan13

Love it <3

1
#5 opened 3 months ago by
cutycat2000x

This is wild, a new paradigm emerges!

1
#4 opened 3 months ago by
blackcat1402

just to say that you did a marvellous job with this one, thank you for allowing us to experience it.

1
#2 opened 3 months ago by
asidaddy

Are you planning to open source your veRL fork?

1
#1 opened 3 months ago by
philschmid
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs