Article
15
Félix Marty
fxmarty
AI & ML interests
Neural network compression
Source separation
Recent Activity
updated
a model
about 15 hours ago
fxmarty/Llama-3.1-70B-Instruct-2-layers-mxfp6
published
a model
about 15 hours ago
fxmarty/Llama-3.1-70B-Instruct-2-layers-mxfp6
updated
a model
5 days ago
fxmarty/Mixtral-8x7B-Instruct-v0.1-FP8-KV-2-layers
Organizations
Articles 4
Article
4
AMD + 🤗: Large Language Models Out-of-the-Box Acceleration with AMD GPU
models
125
fxmarty/Llama-3.1-70B-Instruct-2-layers-mxfp6
3B
•
Updated
fxmarty/Mixtral-8x7B-Instruct-v0.1-FP8-KV-2-layers
3B
•
Updated
•
165
fxmarty/logs
Updated
fxmarty/Mixtral-8x7B-Instruct-v0.1-2-layers
3B
•
Updated
•
6
fxmarty/Llama-3.1-70B-Instruct-2-layers
4B
•
Updated
•
8
fxmarty/Llama-3.1-405B-Instruct-2-layers
11B
•
Updated
•
11
fxmarty/Llama-4-Scout-17B-16E-Instruct-2-layers-mxfp4
5B
•
Updated
•
21
fxmarty/deepseek_r1_3_layers_mxfp4
8B
•
Updated
•
1.75k
•
1
fxmarty/qwen_1.5-moe-a2.7b-mxfp4
8B
•
Updated
•
1.47k
fxmarty/tiny-llama-head-dim-32
0.0B
•
Updated
•
16