fxmarty/logs
Updated
Félix Marty
fxmarty
AI & ML interests
Neural network compression
Source separation
Recent Activity
updated
a model
about 11 hours ago
fxmarty/logs
updated
a model
4 days ago
fxmarty/Mixtral-8x7B-Instruct-v0.1-2-layers
published
a model
4 days ago
fxmarty/Mixtral-8x7B-Instruct-v0.1-2-layers
Organizations
fxmarty/Mixtral-8x7B-Instruct-v0.1-2-layers
Updated
•
5
fxmarty/Llama-3.1-70B-Instruct-2-layers
Updated
•
9
fxmarty/Llama-3.1-405B-Instruct-2-layers
Updated
•
12
fxmarty/Llama-4-Scout-17B-16E-Instruct-2-layers-mxfp4
Updated
•
26
fxmarty/deepseek_r1_3_layers_mxfp4
Updated
•
1.65k
•
1
fxmarty/qwen_1.5-moe-a2.7b-mxfp4
Updated
•
1.54k
fxmarty/tiny-llama-head-dim-32
Updated
•
31
fxmarty/small-llama-testing
Updated
•
2.59k
fxmarty/Qwen1.5-0.5B-tiny-testing
Updated
•
11
fxmarty/opt-125m-tiny-testing
Updated
•
9
fxmarty/llama-small-int4-per-group-sym-awq
Updated
•
23
fxmarty/llama-tiny-int4-per-group-sym
Updated
•
19
fxmarty/llama-small-int4-per-group-sym-awq-old
Updated
•
14
fxmarty/llama-tiny-w-int8-b-int8-per-tensor
Updated
•
13
fxmarty/llama-tiny-w-fp8-a-fp8
Updated
•
27
fxmarty/llama-tiny-w-fp8-a-fp8-o-fp8
Updated
•
34
fxmarty/llama-tiny-w-int8-per-tensor
Updated
•
62
fxmarty/imagenet-classes
Updated
fxmarty/quark-assets
Updated
fxmarty/quark-legacy-fp8
Updated
•
7
fxmarty/quark-legacy-awq
Updated
•
75
fxmarty/quark-legacy-int8
Updated
•
32
fxmarty/dummy-config-awq
Updated
•
36
fxmarty/llama-tiny-testing-quark-indev
Updated
•
14
fxmarty/tiny-llama-fast-tokenizer
Text Generation
•
Updated
•
30.8k
•
10
fxmarty/clip-vision-model-tiny
Feature Extraction
•
Updated
•
3.04k
fxmarty/softmax-pytorch-numerical-stability
Updated
fxmarty/debug-_transformer_encoder_layer_fwd
Updated
fxmarty/tiny-dummy-qwen2
Text Generation
•
Updated
•
127k
•
1