Olafangensan/GLM-4.7-Flash-heretic-GGUF
Text Generation
•
30B
•
Updated
•
1.02k
•
1
Olaf Kowalsky
Olafangensan
AI & ML interests
None yet
Recent Activity
new activity
3 days ago
DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF:Oh hey, that's me!
updated
a model
4 days ago
Olafangensan/GLM-4.7-Flash-heretic-GGUF
published
a model
5 days ago
Olafangensan/GLM-4.7-Flash-heretic-GGUF
Organizations
None yet
Oh hey, that's me!
đź‘Ť
3
1
#1 opened 3 days ago
by
Olafangensan
updated
a
model
4 days ago
published
a
model
5 days ago
updated
a
model
5 days ago
published
a
model
5 days ago
HyperNova-60B.IQ4_XS crashing on newest llama.cpp
#1 opened 22 days ago
by
Olafangensan
How to skip the thinking?
1
#2 opened 5 months ago
by
Olafangensan
reacted to
ccocks-deca's
post with 🔥
5 months ago
Post
2885
12 hours ago:
Annnnnd... here it is! https://huggingface.co/deca-ai/3-alpha-ultra —the largest AI model in the world by
deca-ai
, clocking in at a whopping 4.6T parameters. Apologies for the delay, but we’re stoked to finally drop this, even in its alpha stage. Before you dive in, here are a few things to keep in mind:
1. **No commercial use yet**: We're still working on Deca 2.5 (Proprietary), and releasing Deca 3 for commercial use right now would impact that. Once Deca 3.5 hits in early '26, we’ll be opening it up with a more permissive license.
2. **Built on existing models**: Deca 3 isn’t a ground-up creation—it’s a huge step forward, building on what’s already out there.
3. **It’s experimental**: As much as we’re hyped about its scale, it’s still in testing.
4. **DynaMoE architecture**: Run a (very) small part of the model with 64GB of RAM/VRAM (when quantized - quants coming soon), or the whole thing with 1TB. It’s that scalable.
5. **Not widely supported yet**: Frameworks like vLLM and Transformers aren’t compatible with Deca 3 at the moment, so until we drop the DynaMoE software (beta coming soon), it’s mostly just a concept.
We’re super excited to see what you do with it once the full setup’s ready. Hang tight, and stay tuned!
Something big* coming
*big = biggest in the worldAnnnnnd... here it is! https://huggingface.co/deca-ai/3-alpha-ultra —the largest AI model in the world by
1. **No commercial use yet**: We're still working on Deca 2.5 (Proprietary), and releasing Deca 3 for commercial use right now would impact that. Once Deca 3.5 hits in early '26, we’ll be opening it up with a more permissive license.
2. **Built on existing models**: Deca 3 isn’t a ground-up creation—it’s a huge step forward, building on what’s already out there.
3. **It’s experimental**: As much as we’re hyped about its scale, it’s still in testing.
4. **DynaMoE architecture**: Run a (very) small part of the model with 64GB of RAM/VRAM (when quantized - quants coming soon), or the whole thing with 1TB. It’s that scalable.
5. **Not widely supported yet**: Frameworks like vLLM and Transformers aren’t compatible with Deca 3 at the moment, so until we drop the DynaMoE software (beta coming soon), it’s mostly just a concept.
We’re super excited to see what you do with it once the full setup’s ready. Hang tight, and stay tuned!
- 3 replies
Why are the file sizes so similar?
1
#1 opened 6 months ago
by
Olafangensan
Is the prompt format correct?
3
#1 opened 7 months ago
by
Olafangensan
REALLY slow with flash attention and quantized cache.
7
#2 opened 11 months ago
by
Olafangensan
This model is SUCH A TRYHARD
đź§
2
3
#1 opened 11 months ago
by
Olafangensan
recommended generation parameters
7
#5 opened 11 months ago
by
erichartford
Long output issues
1
#1 opened about 1 year ago
by
Olafangensan
Feedback
11
#1 opened about 1 year ago
by
xxx777xxxASD
reacted to
davanstrien's
post with ❤️
about 1 year ago
Post
2542
First dataset for the new Hugging Face Bluesky community organisation: https://huggingface.co/datasets/bluesky-community/one-million-bluesky-posts 🦋
đź“Š 1M public posts from Bluesky's firehose API
🔍 Includes text, metadata, and language predictions
🔬 Perfect to experiment with using ML for Bluesky 🤗
Excited to see people build more open tools for a more open social media platform!
đź“Š 1M public posts from Bluesky's firehose API
🔍 Includes text, metadata, and language predictions
🔬 Perfect to experiment with using ML for Bluesky 🤗
Excited to see people build more open tools for a more open social media platform!
liked
a
model
over 1 year ago
Better performance with ChatML for novel writing.
#6 opened over 1 year ago
by
Olafangensan
Feedback
47
#1 opened over 1 year ago
by
MarinaraSpaghetti
GGUF quants version?
đź‘Ť
1
2
#1 opened over 1 year ago
by
celsowm