mlx-community/QwQ-32B-6bit
Text Generation
•
Updated
•
437
•
3
Dan Ofer
GrimSqueaker
AI & ML interests
Bioinformatics, Neurobiology, AutoML, Feature engineering, Proteins, NLP
Recent Activity
liked
a model
4 days ago
mlx-community/QwQ-32B-6bit
liked
a dataset
7 days ago
ctheodoris/Genecorpus-30M
liked
a model
7 days ago
ctheodoris/Geneformer
Organizations
None yet
GrimSqueaker's activity
liked
a
model
4 days ago
liked
a
dataset
7 days ago
liked
a
model
7 days ago
liked
a
model
9 days ago
liked
2
datasets
9 days ago
liked
2
models
10 days ago
liked
a
model
11 days ago
liked
a
model
19 days ago
liked
2
models
about 1 month ago
liked
6
models
about 2 months ago
mlx-community/DeepSeek-R1-Distill-Qwen-32B-6bit
Updated
•
661
•
1
mlx-community/Unsloth-DeepSeek-R1-Distill-Qwen-32B-4bit
Text Generation
•
Updated
•
109
•
1
unsloth/DeepSeek-R1-Distill-Llama-70B-GGUF
Updated
•
647k
•
73
unsloth/DeepSeek-R1-Distill-Qwen-32B-GGUF
Updated
•
235k
•
122
Qwen/Qwen2.5-32B
Text Generation
•
Updated
•
116k
•
123
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
Text Generation
•
Updated
•
1.59M
•
•
1.26k
commented on
Train 400x faster Static Embedding Models with Sentence Transformers
about 2 months ago
I'd just start with modernBert large though, easier and strong base. Less faffing about. Also big vocab <3
commented on
Train 400x faster Static Embedding Models with Sentence Transformers
about 2 months ago
They do PCA (prior to the zipf weighting) and explicitly state that they found that it improved perf.