DeepSeek-R1-ReDistill
Collection
Re-distilled DeepSeek R1 models
•
3 items
•
Updated
•
4
Mobius Labs GmbH
company
AI & ML interests
Computer Vision, LLMs, Multimodal Models, Model Compression
Recent Activity
View all activity
mobiuslabsgmbh's activity
mobicham
updated
a
collection
about 2 hours ago
mobicham
published
2
models
about 2 hours ago
mobicham
updated
a
model
about 5 hours ago
mobicham
updated
2
models
about 7 hours ago
mobicham
updated
a
collection
3 days ago
mobicham
published
a
model
3 days ago
Jilt
updated
a
model
4 months ago
Post
2069
Releasing HQQ Llama-3.1-70b 4-bit quantized version! Check it out at
mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq.
Achieves 99% of the base model performance across various benchmarks! Details in the model card.
Achieves 99% of the base model performance across various benchmarks! Details in the model card.
Post
1790
Excited to announce the release of our high-quality Llama-3.1 8B 4-bit HQQ/calibrated quantized model! Achieving an impressive 99.3% relative performance to FP16, it also delivers the fastest inference speed for transformers.
mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib
mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib
- 1 reply
Jilt
updated
a
dataset
9 months ago
appoose
updated
a
Space
10 months ago
mobicham
updated
a
model
10 months ago
mobicham
updated
4
models
11 months ago
mobiuslabsgmbh/aanaphi2-v0.1
Text Generation
•
Updated
•
197
•
28
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-3bit-metaoffload-HQQ
Text Generation
•
Updated
•
14
•
13
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ
Text Generation
•
Updated
•
15
•
20
mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bit-metaoffload-HQQ
Text Generation
•
Updated
•
21
•
15