Aman Rangapur
amanrangapur
AI & ML interests
Generative AI, NLP, AI for good.
Recent Activity
updated
a Space
about 10 hours ago
allenai/README
published
a Space
about 10 hours ago
allenai/README
updated
a model
1 day ago
allenai/OLMo-2-0325-32B
Organizations
amanrangapur's activity
Using this model in LM Studio does not complete (stuck at PromptProcessing: 99.9517)
2
#15 opened 19 days ago
by
sheyenrath

Local execution issue
2
#13 opened 20 days ago
by
binzhango

Request: DOI
#17 opened 15 days ago
by
Revok8935

Cool Model
1
#4 opened 29 days ago
by
binzhango

please create a quantized version, preferably using bitsandbytes!
4
#3 opened 29 days ago
by
ctranslate2-4you
Some edge case is not good
1
#2 opened 29 days ago
by
bash99
32b, 4k ctx?
6
#2 opened 14 days ago
by
lucyknada

add LGAI-EXAONE/EXAONE-3.5-32B-Instruct as another baseline?
1
#3 opened 13 days ago
by
yhg0112

multi language support
1
#4 opened 13 days ago
by
devops724
Steps stage 1 incomplete weights?
3
#4 opened 12 days ago
by
KnutJaegersberg

Can't run in llama.cpp, wrong tensor shape
13
#1 opened 14 days ago
by
bartowski

bruh there is pic of a WHAT in first doc
2
#1 opened 21 days ago
by
kavinask007

Local inference on Intel iGPU
1
#12 opened 23 days ago
by
luweigen
Excellent for its size!
2
#1 opened about 1 month ago
by
MurphyGM
VLLM serving Tulu3 Llama 405B
1
#3 opened about 1 month ago
by
JettLam
Many wrong answers
4
#4 opened about 1 month ago
by
smartsurfer
fp16 or bf16 version?
3
#6 opened 6 months ago
by
xiangli
How to perform forward pass when loading the model with bfloat16?
1
#12 opened 6 months ago
by
etoml
Request: DOI
#14 opened 5 months ago
by
Arslanbey123
GGML_ASSERT errors running on llama.cpp 27e8a23300e30cd6ff6107ce262acf832ca60597
1
#1 opened about 1 month ago
by
SamPurkis