Carl Silva PRO
silvacarl
AI & ML interests
anything to do with applying ML to speech to text in the healthcare field.
Organizations
no vllm?
2
#7 opened 4 months ago
by
silvacarl
SFT notebooks
2
#1 opened 12 months ago
by
silvacarl
no attribute tokenizer?
11
#1 opened about 1 year ago
by
silvacarl
vllm call for multiple GPUs, just fyi.
1
#16 opened about 1 year ago
by
silvacarl
Hosting an Inference endpoint
11
#6 opened over 2 years ago
by
lukehansen
Is there any vllm support for this version?
9
#49 opened almost 2 years ago
by
Aloukik21
Loading and Running the Grok-1 Open-Weights Model
6
#54 opened over 1 year ago
by
Ateeqq
extremely variable response time for inference?
9
#21 opened almost 2 years ago
by
silvacarl
API and prompt format?
1
#11 opened about 2 years ago
by
silvacarl
How to fine tune ?
14
#12 opened about 2 years ago
by
NickyNicky
any idea how to test this for inferencing using vllm?
3
#1 opened about 2 years ago
by
silvacarl
key error
👍
8
15
#2 opened about 2 years ago
by
NS-Y
Prompt for instructions ?
👍
10
4
#1 opened over 2 years ago
by
asach
Various Prompt Formats
8
#24 opened over 2 years ago
by
gsaivinay
GPU requirement for simply running the model
27
#9 opened over 2 years ago
by
abhi24
I am getting the CUDA OUT-Of-Memory on Tesla T4 but only with these prompts...
18
#5 opened over 2 years ago
by
AayushShah
Licensing? Commercial use?
2
#4 opened over 2 years ago
by
xjdeng
Few shot learning
4
#1 opened over 2 years ago
by
iRanadheer