A collection of MoE+MLA models, serving as testing proxies for DeepSeek-V3/R1
Thien Tran
gaunernst
AI & ML interests
None yet
Recent Activity
new activity
20 days ago
gaunernst/gemma-3-27b-it-qat-autoawq:Broken results with vLLM
new activity
25 days ago
gaunernst/gemma-3-27b-it-qat-autoawq:Cannot find the config file for awq
new activity
25 days ago
gaunernst/gemma-3-27b-it-int4-awq:Model running badly on vLLM
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 • 0.4B • Updated • 2.62k • 2 -
gaunernst/gemma-3-4b-it-int4-awq
Image-Text-to-Text • 2B • Updated • 1.43k • 1 -
gaunernst/gemma-3-12b-it-int4-awq
Image-Text-to-Text • 3B • Updated • 2.39k • 16 -
gaunernst/gemma-3-27b-it-int4-awq
Image-Text-to-Text • 6B • Updated • 5.33k • 28
-
gaunernst/vit_small_patch8_gap_112.cosface_ms1mv3
Image Feature Extraction • 0.0B • Updated • 276 • 2 -
gaunernst/vit_tiny_patch8_112.cosface_ms1mv3
Image Feature Extraction • 0.0B • Updated • 11 • 1 -
gaunernst/vit_tiny_patch8_112.arcface_ms1mv3
Image Feature Extraction • 0.0B • Updated • 106 • 2 -
gaunernst/vit_tiny_patch8_112.adaface_ms1mv3
Image Feature Extraction • 0.0B • Updated • 7 • 1
-
nvidia/Llama-3.1-Minitron-4B-Width-Base
Text Generation • 5B • Updated • 2.54k • 191 -
nvidia/Llama-3.1-Minitron-4B-Depth-Base
Text Generation • 5B • Updated • 2.35k • 21 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 14.5M • • 4.46k -
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 852k • • 1.73k
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 • 0.4B • Updated • 23 -
gaunernst/gemma-3-4b-it-qat-autoawq
Image-Text-to-Text • 2B • Updated • 1.02k • 1 -
gaunernst/gemma-3-12b-it-qat-autoawq
Image-Text-to-Text • 3B • Updated • 1.6k • 6 -
gaunernst/gemma-3-27b-it-qat-autoawq
Image-Text-to-Text • 6B • Updated • 2.22k • 10
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 • 0.4B • Updated • 23 -
gaunernst/gemma-3-4b-it-qat-autoawq
Image-Text-to-Text • 2B • Updated • 1.02k • 1 -
gaunernst/gemma-3-12b-it-qat-autoawq
Image-Text-to-Text • 3B • Updated • 1.6k • 6 -
gaunernst/gemma-3-27b-it-qat-autoawq
Image-Text-to-Text • 6B • Updated • 2.22k • 10
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 • 0.4B • Updated • 2.62k • 2 -
gaunernst/gemma-3-4b-it-int4-awq
Image-Text-to-Text • 2B • Updated • 1.43k • 1 -
gaunernst/gemma-3-12b-it-int4-awq
Image-Text-to-Text • 3B • Updated • 2.39k • 16 -
gaunernst/gemma-3-27b-it-int4-awq
Image-Text-to-Text • 6B • Updated • 5.33k • 28
https://arxiv.org/abs/1908.08962
-
gaunernst/vit_small_patch8_gap_112.cosface_ms1mv3
Image Feature Extraction • 0.0B • Updated • 276 • 2 -
gaunernst/vit_tiny_patch8_112.cosface_ms1mv3
Image Feature Extraction • 0.0B • Updated • 11 • 1 -
gaunernst/vit_tiny_patch8_112.arcface_ms1mv3
Image Feature Extraction • 0.0B • Updated • 106 • 2 -
gaunernst/vit_tiny_patch8_112.adaface_ms1mv3
Image Feature Extraction • 0.0B • Updated • 7 • 1
-
nvidia/Llama-3.1-Minitron-4B-Width-Base
Text Generation • 5B • Updated • 2.54k • 191 -
nvidia/Llama-3.1-Minitron-4B-Depth-Base
Text Generation • 5B • Updated • 2.35k • 21 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 14.5M • • 4.46k -
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 852k • • 1.73k