4
Mediapipe Face Landmark/Skin Transform
š»
Transform face landmark/skin,half of FaceSwap
Akihito Miyazaki PRO
Akjava
AI & ML interests
Iām creating a 3D/Voice Conversational AI Presentation Avatar with Diagrams
Recent Activity
updated
a Space
1 day ago
Akjava/mediapipe-face-skin-transform
liked
a Space
4 days ago
yanze/PuLID-FLUX
liked
a Space
5 days ago
ovi054/Wan2.1-Image
Organizations
None yet
Akjava's activity
updated
a
Space
1 day ago
liked
a
Space
4 days ago
liked
a
Space
5 days ago
liked
a
Space
7 days ago
liked
a
Space
10 days ago
liked
a
model
12 days ago
liked
2
Spaces
15 days ago
Suggestions Needed.
1
#4 opened 17 days ago
by
DyrusQZ
liked
a
model
17 days ago
liked
a
Space
18 days ago
posted
an
update
22 days ago
Post
479
I've shared Hugging Face Spaces for CPU-based RAG and T5/Flan-T5 models. The smolagents-rag space sometimes produces high-quality answers, but it can be slow. Qwen2.5-0.5B is as fast as a CPU implementation and generates answers of acceptable quality. I've found that Gemma3-4B produces significantly more stable answers than the 1B version.
Rag
Akjava/Gemma3-4B-llamacpp-cpu-rag-smolagents
Akjava/Qwen2.5-0.5B-Rag-Thinking-Flan-T5
t5/flan-t5
Akjava/llamacpp-flan-t5-large-grammar-synthesis
Akjava/llamacpp-madlad400-3b-mt-2jp
Huggingface Free CPU Limitations
When duplicating a space, the build process(llama-cpp-python) can occasionally become stuck, requiring a manual restart to finish.
Spaces may unexpectedly stop functioning or even be deleted, leading to the need to rework them. Refer to issue for more information.
Rag
Akjava/Gemma3-4B-llamacpp-cpu-rag-smolagents
Akjava/Qwen2.5-0.5B-Rag-Thinking-Flan-T5
t5/flan-t5
Akjava/llamacpp-flan-t5-large-grammar-synthesis
Akjava/llamacpp-madlad400-3b-mt-2jp
Huggingface Free CPU Limitations
When duplicating a space, the build process(llama-cpp-python) can occasionally become stuck, requiring a manual restart to finish.
Spaces may unexpectedly stop functioning or even be deleted, leading to the need to rework them. Refer to issue for more information.
published
4
Spaces
22 days ago
Llamacpp-madlad400-3b-mt
ā”
madlad400-3b-mt on Llama.cpp CPU
llhamacpp-flan-t5-large-grammar-synthesis
š
flan-t5-large-grammar-synthesis on Llama.cpp CPU
2
Gemma3-4B-llamacpp-cpu-rag-smolagents
ā”
Rag example with Gemma3-4B and Smolagents
1
Qwen2.5-0.5B-Rag-Thinking-llamacpp-cpu-rag-Flan-T5
ā”
Rag example with Qwen2.5-0.5B-Rag-Thinking +
updated
4
Spaces
22 days ago
1
Qwen2.5-0.5B-Rag-Thinking-llamacpp-cpu-rag-Flan-T5
ā”
Rag example with Qwen2.5-0.5B-Rag-Thinking +
Llamacpp-madlad400-3b-mt
ā”
madlad400-3b-mt on Llama.cpp CPU
2
Gemma3-4B-llamacpp-cpu-rag-smolagents
ā”
Rag example with Gemma3-4B and Smolagents
llhamacpp-flan-t5-large-grammar-synthesis
š
flan-t5-large-grammar-synthesis on Llama.cpp CPU