Running
2
🔹
AboutAetherArchitectural
Welcome to the AetherArchitectural Community!
AetherArchitectural
community
Verified
AI & ML interests
Aetherarchio, Lewdiculous and FantasiaFoundry's general AI, ML and LLM related community projects. [[email protected]]
Recent Activity
View all activity
AetherArchitectural's activity
Lewdiculous
updated
a
Space
5 days ago
Lewdiculous
updated
a
model
6 days ago
Lewdiculous
updated
a
collection
6 days ago
Lewdiculous
posted
an
update
6 days ago
Post
1699
Hello fellow LLMers, just a quick notice that some of my activity will be moved into the AetherArchitectural Commuity and split with
@Aetherarchio
.
[here] https://huggingface.co/AetherArchitectural
All activity should be visible in the left side of my profile.
[here] https://huggingface.co/AetherArchitectural
All activity should be visible in the left side of my profile.
- 1 reply
Aetherarchio
updated
a
model
8 days ago
Aetherarchio
updated
a
collection
8 days ago
Aetherarchio
updated
a
model
8 days ago
Welcome to AetherArchitectural!
#1 opened 8 days ago
by
Aetherarchio
Aetherarchio
updated
a
Space
8 days ago
Emphasis DFSM - Nexesenex/kobold.cpp
5
#18 opened 5 months ago
by
Lewdiculous
Lewdiculous
updated
a
collection
about 1 month ago
Sampling Resources and Conjecture
44
#2 opened 8 months ago
by
Clevyby
Llama-3 SillyTavern Presets Sharing
39
#5 opened 8 months ago
by
Lewdiculous
Lewdiculous
updated
a
model
about 1 month ago
Lewdiculous
updated
a
collection
about 1 month ago
FantasiaFoundry
updated
a
model
about 1 month ago
Lewdiculous
posted
an
update
7 months ago
Post
42676
More context for your Pascal GPU or older!
Update: Now available in the official releases of KoboldCpp!
[releases] https://github.com/LostRuins/koboldcpp/releases/latest
These are great news for all the users with GTX 10XX, P40...
Flash Attention implementation for older NVIDIA GPUs without requiring Tensor Cores has come to llama.cpp in the last few days, and should be merged in the next version of KoboldCpp, you can already try it with another fork or by building it.
[Mentioned KCPP fork] https://github.com/Nexesenex/kobold.cpp/releases/latest
[PR] https://github.com/ggerganov/llama.cpp/pull/7188
You should expect less VRAM usage for the same context, allowing you to experience higher contexts with your current GPU.
There have also been reported final tokens/second speed improvements for inference, so that's also grand!
If you have tried it, I'd like to hear your experiences with --flashattention so far, especially for this implementation and for the large number of Pascal (GTX 10XX, P40...) cards.
Discussion linked bellow, with more links to relevant information:
https://huggingface.co/LWDCLS/LLM-Discussions/discussions/11
Cheers!
Update: Now available in the official releases of KoboldCpp!
[releases] https://github.com/LostRuins/koboldcpp/releases/latest
These are great news for all the users with GTX 10XX, P40...
Flash Attention implementation for older NVIDIA GPUs without requiring Tensor Cores has come to llama.cpp in the last few days, and should be merged in the next version of KoboldCpp, you can already try it with another fork or by building it.
[Mentioned KCPP fork] https://github.com/Nexesenex/kobold.cpp/releases/latest
[PR] https://github.com/ggerganov/llama.cpp/pull/7188
You should expect less VRAM usage for the same context, allowing you to experience higher contexts with your current GPU.
There have also been reported final tokens/second speed improvements for inference, so that's also grand!
If you have tried it, I'd like to hear your experiences with --flashattention so far, especially for this implementation and for the large number of Pascal (GTX 10XX, P40...) cards.
Discussion linked bellow, with more links to relevant information:
https://huggingface.co/LWDCLS/LLM-Discussions/discussions/11
Cheers!
-
- 24 replies
Lewdiculous
posted
an
update
8 months ago
Post
43907
Updated: Lumimaid and TheSpice-v0.8.3
I have uploaded version 2 (v2) files for the Llama-3-Lumimaid-8B-v0.1-OAS GGUF Imatrix quants.
[model] Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix
You can recognize the new files by their
Imatrix data was generated from the FP16 and conversions directly from the BF16.
Hopefully avoiding any losses in the model conversion, as has been the recently discussed topic on Llama-3 and GGUF lately.
This is more disk and compute intensive so lets hope we get GPU inference support for BF16 models in llama.cpp.
If you are able to test them and noticed any issues compared to the original quants, let me know in the corresponding discussions.
---
Additionally, L3-TheSpice-8b-v0.8.3 GGUF Imatrix quants were also updated.
[model] Lewdiculous/L3-TheSpice-8b-v0.8.3-GGUF-IQ-Imatrix
I have uploaded version 2 (v2) files for the Llama-3-Lumimaid-8B-v0.1-OAS GGUF Imatrix quants.
[model] Lewdiculous/Llama-3-Lumimaid-8B-v0.1-OAS-GGUF-IQ-Imatrix
You can recognize the new files by their
v2 prefix.Imatrix data was generated from the FP16 and conversions directly from the BF16.
Hopefully avoiding any losses in the model conversion, as has been the recently discussed topic on Llama-3 and GGUF lately.
This is more disk and compute intensive so lets hope we get GPU inference support for BF16 models in llama.cpp.
If you are able to test them and noticed any issues compared to the original quants, let me know in the corresponding discussions.
---
Additionally, L3-TheSpice-8b-v0.8.3 GGUF Imatrix quants were also updated.
[model] Lewdiculous/L3-TheSpice-8b-v0.8.3-GGUF-IQ-Imatrix
-
- 7 replies