A collection of MoE+MLA models, serving as testing proxies for DeepSeek-V3/R1
Thien Tran
gaunernst
EclecticMarsupialNeurosis's profile picture
amaralibey's profile picture
bofenghuang's profile picture
·
AI & ML interests
None yet
Recent Activity
updated
a Space
about 1 month ago
gaunernst/AudioMAE-AudioSet20k
updated
a Space
about 1 month ago
gaunernst/kv-cache-calculator
updated
a Space
about 1 month ago
gaunernst/LayoutLMv2-FUNSD
Organizations
These are converted from the official QAT INT4 Flax checkpoints on Kaggle. Supported formats: AutoAWQ, GGUF
-
gaunernst/gemma-3-1b-it-int4-awq
Text Generation • Updated • 58 • 2 -
gaunernst/gemma-3-4b-it-int4-awq
Image-Text-to-Text • Updated • 33.3k • 5 -
gaunernst/gemma-3-12b-it-int4-awq
Image-Text-to-Text • 12B • Updated • 5.29k • 22 -
gaunernst/gemma-3-27b-it-int4-awq
Image-Text-to-Text • 6B • Updated • 21k • 37
-
gaunernst/vit_small_patch8_gap_112.cosface_ms1mv3
Image Feature Extraction • Updated • 91 • 2 -
gaunernst/vit_tiny_patch8_112.cosface_ms1mv3
Image Feature Extraction • Updated • 53 • 2 -
gaunernst/vit_tiny_patch8_112.arcface_ms1mv3
Image Feature Extraction • Updated • 32 • 3 -
gaunernst/vit_tiny_patch8_112.adaface_ms1mv3
Image Feature Extraction • Updated • 18 • 2
-
nvidia/Llama-3.1-Minitron-4B-Width-Base
Text Generation • 5B • Updated • 1.72k • 193 -
nvidia/Llama-3.1-Minitron-4B-Depth-Base
Text Generation • 5B • Updated • 309 • 21 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 9.69M • • 5.29k -
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 2.38M • • 2.02k
Convert official Gemma 3 QAT GGUF to AutoAWQ and compressed-tensors format for ease of deployment
-
gaunernst/gemma-3-1b-it-qat-autoawq
Text Generation • Updated • 11 -
gaunernst/gemma-3-4b-it-qat-autoawq
Image-Text-to-Text • Updated • 224 • 1 -
gaunernst/gemma-3-12b-it-qat-autoawq
Image-Text-to-Text • 12B • Updated • 954 • 7 -
gaunernst/gemma-3-27b-it-qat-autoawq
Image-Text-to-Text • 27B • Updated • 8.65k • 12
https://arxiv.org/abs/1908.08962
A collection of MoE+MLA models, serving as testing proxies for DeepSeek-V3/R1
Convert official Gemma 3 QAT GGUF to AutoAWQ and compressed-tensors format for ease of deployment
-
gaunernst/gemma-3-1b-it-qat-autoawq
Text Generation • Updated • 11 -
gaunernst/gemma-3-4b-it-qat-autoawq
Image-Text-to-Text • Updated • 224 • 1 -
gaunernst/gemma-3-12b-it-qat-autoawq
Image-Text-to-Text • 12B • Updated • 954 • 7 -
gaunernst/gemma-3-27b-it-qat-autoawq
Image-Text-to-Text • 27B • Updated • 8.65k • 12
These are converted from the official QAT INT4 Flax checkpoints on Kaggle. Supported formats: AutoAWQ, GGUF
-
gaunernst/gemma-3-1b-it-int4-awq
Text Generation • Updated • 58 • 2 -
gaunernst/gemma-3-4b-it-int4-awq
Image-Text-to-Text • Updated • 33.3k • 5 -
gaunernst/gemma-3-12b-it-int4-awq
Image-Text-to-Text • 12B • Updated • 5.29k • 22 -
gaunernst/gemma-3-27b-it-int4-awq
Image-Text-to-Text • 6B • Updated • 21k • 37
https://arxiv.org/abs/1908.08962
-
gaunernst/vit_small_patch8_gap_112.cosface_ms1mv3
Image Feature Extraction • Updated • 91 • 2 -
gaunernst/vit_tiny_patch8_112.cosface_ms1mv3
Image Feature Extraction • Updated • 53 • 2 -
gaunernst/vit_tiny_patch8_112.arcface_ms1mv3
Image Feature Extraction • Updated • 32 • 3 -
gaunernst/vit_tiny_patch8_112.adaface_ms1mv3
Image Feature Extraction • Updated • 18 • 2
-
nvidia/Llama-3.1-Minitron-4B-Width-Base
Text Generation • 5B • Updated • 1.72k • 193 -
nvidia/Llama-3.1-Minitron-4B-Depth-Base
Text Generation • 5B • Updated • 309 • 21 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 9.69M • • 5.29k -
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 2.38M • • 2.02k