Krutrim TTS
📉
TTS for Indic Language from Ola Krutrim
Niranjan Sarkar PRO
bharatcoder
AI & ML interests
None yet
Recent Activity
updated
a Space
4 days ago
bharatcoder/Krutrim_TTS
published
a Space
4 days ago
bharatcoder/Krutrim_TTS
commented on
an
article
4 days ago
How to Build an MCP Server with Gradio
Organizations
None yet
bharatcoder's activity
updated
a
Space
4 days ago
published
a
Space
4 days ago
commented on
How to Build an MCP Server with Gradio
4 days ago
Copying the config to claude desktop, gives me error.
liked
a
Space
6 days ago
JetBrains/Mellum-4b-base
6
#1383 opened 6 days ago
by
bharatcoder
deepcogito/cogito-v1-preview-qwen-32B
6
1
#550 opened 27 days ago
by
bharatcoder
liked
a
model
29 days ago
liked
a
model
about 1 month ago
liked
a
model
about 2 months ago
liked
a
Space
about 2 months ago
upvoted
a
collection
about 2 months ago
how to generate api key by duplicating the space ?
14
#9 opened 2 months ago
by
deeduckme
Make it Duplicatable without DASHSCOPE API
1
4
#6 opened 2 months ago
by
jujutechnology
upvoted
an
article
2 months ago
Article
SmolVLM2: Bringing Video Understanding to Every Device
•
243
liked
a
model
3 months ago
upvoted
a
collection
3 months ago
[FEEDBACK] Inference Providers
16
112
#49 opened 4 months ago
by
julien-c
liked
a
Space
3 months ago
reacted to
fdaudens's
post with ❤️
3 months ago
Post
9276
Yes, DeepSeek R1's release is impressive. But the real story is what happened in just 7 days after:
- Original release: 8 models, 540K downloads. Just the beginning...
- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5M—nearly 5X the originals.
The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.
When you empower builders, innovation explodes. For everyone. 🚀
The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version — 1M downloads alone.
- Original release: 8 models, 540K downloads. Just the beginning...
- The community turned those open-weight models into +550 NEW models on Hugging Face. Total downloads? 2.5M—nearly 5X the originals.
The reason? DeepSeek models are open-weight, letting anyone build on top of them. Interesting to note that the community focused on quantized versions for better efficiency & accessibility. They want models that use less memory, run faster, and are more energy-efficient.
When you empower builders, innovation explodes. For everyone. 🚀
The most popular community model? @bartowski 's DeepSeek-R1-Distill-Qwen-32B-GGUF version — 1M downloads alone.
- 5 replies