Arthur Zucker
ArthurZ
AI & ML interests
None yet
Recent Activity
liked
a model
2 days ago
google/gemma-3-27b-it
liked
a model
12 days ago
microsoft/Magma-8B
liked
a model
28 days ago
Qwen/Qwen2.5-3B
Organizations
ArthurZ's activity
Fastest way for inference?
3
#28 opened about 1 month ago
by
psycy
model-00078-of-000163.safetensors not marked safe?
2
#80 opened about 1 month ago
by
aborst

Update tokenizer_config.json
#1 opened about 2 months ago
by
ArthurZ

Upload transformers version
8
#3 opened 4 months ago
by
ArthurZ

Upload Meta-Llama-3-8B-Instruct, seqlen = 512, python, w_ compile.png
1
#392 opened 4 months ago
by
kwen2501
Update model weight
8
#13 opened 5 months ago
by
nguyen-brat
Update hidden_act to silu
2
#14 opened 5 months ago
by
ArthurZ

llama.cpp support
9
#1 opened 5 months ago
by
ayyylol

tokenizer_config.json is different from gemma-2-2b-it
2
#8 opened 5 months ago
by
dahara1
How can i use the full 24GB model instead of this separated safetensors files?
1
#8 opened 6 months ago
by
Valadaro
hidden_activation vs hidden_act in config.json
2
#10 opened 6 months ago
by
heheda
How to use safetensors?
2
#13 opened 6 months ago
by
prathi1729
lamma cpp ht to gguf not working
4
#2 opened 6 months ago
by
RameshRajamani
8-kv-heads
8
#14 opened 7 months ago
by
ArthurZ

Update config.json
#17 opened 7 months ago
by
ArthurZ

Config KV Heads should be 8 now?
1
#16 opened 7 months ago
by
tanmaylaud

8 kv heads
2
#13 opened 7 months ago
by
kkokkie2360
8-kv-heads
#15 opened 7 months ago
by
ArthurZ

8-kv-heads
3
#21 opened 8 months ago
by
ArthurZ

8-kv-heads
4
#17 opened 8 months ago
by
ArthurZ
