Hao Jiang
TechxGenus
AI & ML interests
Code Intelligence; Large Language Model; AI Alignment; Efficient Inference
Organizations
None yet
TechxGenus's activity
Bad generated text using tgi
1
#1 opened 30 days ago
by
erfanium
Could you please share the initial weights of one of the experts from jamba?
3
#4 opened about 1 month ago
by
danielpark
Example Code for Initializing from Scratch
1
#3 opened about 1 month ago
by
tanimazsin130
Question about MoA
#2 opened about 1 month ago
by
TechxGenus
Fast Mamba kernels are not available. Make sure to they are installed and that the mamba module is on a CUDA device
1
#2 opened about 2 months ago
by
BalajiAJ
example code missing `import torch`
1
#1 opened about 2 months ago
by
Lyte
[Request] Potential Release Of Training Code?
2
#1 opened about 2 months ago
by
Lyte
Smaller version to ease implementation experiments?
7
#12 opened about 2 months ago
by
compilade
Coding performance of base model?
4
#11 opened about 2 months ago
by
rombodawg
AQLM please for this model
1
#5 opened about 2 months ago
by
AiModelsMarket
What data did you use to finetune this?
2
#4 opened 2 months ago
by
LeeHarrold
can you share the finetune script?
4
#1 opened 2 months ago
by
whybeyoung
Would you be willing to fine-tune a much more capable base gemma model?
5
#1 opened 2 months ago
by
rombodawg
training data
2
#3 opened 3 months ago
by
Meital
If true? Very impressive
5
#1 opened 3 months ago
by
rombodawg