A collection of MoE+MLA models, serving as testing proxies for DeepSeek-V3/R1
Thien Tran
gaunernst
AI & ML interests
None yet
Recent Activity
upvoted a collection about 2 months ago
Gemma 4 updated a Space 5 months ago
gaunernst/AudioMAE-AudioSet20k updated a Space 5 months ago
gaunernst/kv-cache-calculatorOrganizations
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 • 384 • 2 -
gaunernst/gemma-3-4b-it-int4-awq
Image-Text-to-Text • Updated • 2.9k • 7 -
gaunernst/gemma-3-12b-it-int4-awq
Image-Text-to-Text • 12B • Updated • 70.9k • 24 -
gaunernst/gemma-3-27b-it-int4-awq
Image-Text-to-Text • 27B • Updated • 197k • 40
-
gaunernst/vit_small_patch8_gap_112.cosface_ms1mv3
Image Feature Extraction • Updated • 421 • 2 -
gaunernst/vit_tiny_patch8_112.cosface_ms1mv3
Image Feature Extraction • Updated • 11 • 2 -
gaunernst/vit_tiny_patch8_112.arcface_ms1mv3
Image Feature Extraction • Updated • 156 • 4 -
gaunernst/vit_tiny_patch8_112.adaface_ms1mv3
Image Feature Extraction • Updated • 19 • 2
-
nvidia/Llama-3.1-Minitron-4B-Width-Base
Text Generation • 5B • Updated • 2.06k • 194 -
nvidia/Llama-3.1-Minitron-4B-Depth-Base
Text Generation • 5B • Updated • 1.01k • 22 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 10.6M • • 5.9k -
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 1.25M • • 2.21k
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 • 2 -
gaunernst/gemma-3-4b-it-qat-autoawq
Image-Text-to-Text • Updated • 848 • 2 -
gaunernst/gemma-3-12b-it-qat-autoawq
Image-Text-to-Text • 12B • Updated • 220 • 7 -
gaunernst/gemma-3-27b-it-qat-autoawq
Image-Text-to-Text • 27B • Updated • 805 • 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 • 2 -
gaunernst/gemma-3-4b-it-qat-autoawq
Image-Text-to-Text • Updated • 848 • 2 -
gaunernst/gemma-3-12b-it-qat-autoawq
Image-Text-to-Text • 12B • Updated • 220 • 7 -
gaunernst/gemma-3-27b-it-qat-autoawq
Image-Text-to-Text • 27B • Updated • 805 • 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 • 384 • 2 -
gaunernst/gemma-3-4b-it-int4-awq
Image-Text-to-Text • Updated • 2.9k • 7 -
gaunernst/gemma-3-12b-it-int4-awq
Image-Text-to-Text • 12B • Updated • 70.9k • 24 -
gaunernst/gemma-3-27b-it-int4-awq
Image-Text-to-Text • 27B • Updated • 197k • 40
https://arxiv.org/abs/1908.08962
-
gaunernst/vit_small_patch8_gap_112.cosface_ms1mv3
Image Feature Extraction • Updated • 421 • 2 -
gaunernst/vit_tiny_patch8_112.cosface_ms1mv3
Image Feature Extraction • Updated • 11 • 2 -
gaunernst/vit_tiny_patch8_112.arcface_ms1mv3
Image Feature Extraction • Updated • 156 • 4 -
gaunernst/vit_tiny_patch8_112.adaface_ms1mv3
Image Feature Extraction • Updated • 19 • 2
-
nvidia/Llama-3.1-Minitron-4B-Width-Base
Text Generation • 5B • Updated • 2.06k • 194 -
nvidia/Llama-3.1-Minitron-4B-Depth-Base
Text Generation • 5B • Updated • 1.01k • 22 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 10.6M • • 5.9k -
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 1.25M • • 2.21k