Alexandre Marques
alexmarques
AI & ML interests
None yet
Recent Activity
updated
a model
34 minutes ago
nm-testing/Llama-3.1-8B-tldr
published
a model
39 minutes ago
nm-testing/Llama-3.1-8B-tldr
updated
a model
40 minutes ago
nm-testing/Sparse-Llama-3.1-8B-tldr-2of4
Organizations
alexmarques's activity
4a16 quant?
1
#1 opened 19 days ago
by
twhitworth
Error running on A100?
2
#4 opened 20 days ago
by
traphix
What is the difference between Qwen/Qwen3-32B-FP8 and this quatinized modelοΌ
4
#1 opened 26 days ago
by
traphix
How can I repeat the eval results?
3
#2 opened 23 days ago
by
bash99
Where are the safetensors?
π
1
1
#1 opened 23 days ago
by
traphix
Is this a QAT model?
2
#2 opened 30 days ago
by
Downtown-Case
Having trouble running this model with vLLM not sure why
4
#1 opened about 1 month ago
by
zacksiri

Add chat_template to tokenizer_config
π
1
2
#58 opened about 2 months ago
by
alexmarques
KV Cache Quantization - what is the default precision
1
#2 opened 6 months ago
by
deepmage121
Usage of --apply_chat_template in lm_eval benchmarks
1
#1 opened 10 months ago
by
VlSav
how many resources were used for quantizing this model?
1
#4 opened 9 months ago
by
fengyang1995
4k or 128k?
1
#1 opened 9 months ago
by
pavidu
Update README.md
#1 opened 9 months ago
by
nm-research
Llama-3.1 8B quantization?
1
#1 opened 10 months ago
by
ashbo
Language Support
1
#2 opened 10 months ago
by
ashbo
possible problem in description
2
#3 opened 10 months ago
by
kuliev-vitaly
Weird variable name mistakes in code generation
1
#1 opened 10 months ago
by
krana