prjkt
Joined 6 years ago
Karma
13
Submissions
11
Member since
Nov 8
Recent submissions
Comment · 10 days ago
They're competing with NVIDIA (huggingface)
Comment · 1 month ago
how is Jev cheaper if I can run locally. 0.5% prefill, 0.1% decode, 99.4% cached, latency is <20ms
Comment · 1 month ago
"This is discussion; no code changes yet."
vs
Press "Tab"
Comment · 3 months ago
It's like Microsoft banning Vim users that use Azure
Comment · 3 months ago
> If there's such a dramatic hole in demand, who are NVIDIA selling their compute to?
NVIDIA itself is also training foundation models (and open-sourcing them). If there is excess compute available, NVIDIA can increase the scale of such models.
Comment · 7 months ago
In that case, what tokenizer version? What was the temperature set to? topk? topp? FP32? FP16? Quantized? Hopper? Blackwell?
Comment · 1 year ago
What is stopping us from all using IRC again ?
Comment · 1 year ago
does pytorch count
Comment · 1 year ago
Source:
- Training SW [x]
- Inference SW [x]
- Evaluation SW [x]
- Data [x]
Output:
- Weights []
DeepSeek is closed-source with *open-weights*
Comment · 1 year ago
These types of "repositories" should contain some kind of flag/indication that it contains no source code, similar to when a repo is archived