Farid Saud
fsaudm
AI & ML interests
None yet
Organizations
Model issue with 64GB ram
5
#4 opened 3 months ago
by
llama-anon

Something is wrong with the 4bit uploads, 57.9B params???
2
#2 opened 3 months ago
by
fsaudm
OOM on 2xH100
7
#3 opened 3 months ago
by
Maverick17

assert self.quant_method is not None
4
#5 opened 3 months ago
by
Seri0usLee
F*** china!
14
#10 opened 3 months ago
by
Opm84736929

Are the Q4 and Q5 models R1 or R1-Zero
18
#2 opened 5 months ago
by
gng2info
Is this an MOE?
2
#5 opened 5 months ago
by
AlgorithmicKing

Encountering Unknown quantization type, got fp8 - supported types are: XXXXX
🔥
1
3
#1 opened 6 months ago
by
ivanmanu
vLLM help pls :(
4
#6 opened 6 months ago
by
fsaudm
vLLM on A100s
6
#41 opened 6 months ago
by
fsaudm
Failed to run the model with 4 nodes of 8 4090
17
#25 opened 6 months ago
by
aisensiy
vllm
23
#4 opened 6 months ago
by
NikolaSigmoid
vLLM on A100s
4
#19 opened 6 months ago
by
fsaudm
Water and forests
2
#16 opened 6 months ago
by
Dondasse
Model Config Error on VLLM?
➕
1
1
#3 opened 9 months ago
by
rodMetal
Small typo in the examples
👍
1
1
#1 opened 9 months ago
by
jcerruti
How did you make these weights?
2
#3 opened 11 months ago
by
adatkins
Prompt length vs generation? Voice becomes scary at 200 tokens/charactes
👍
2
3
#3 opened 11 months ago
by
fsaudm