Aastha Varma
aastha6
AI & ML interests
LLM: quantization, fine tuning, optimizations | NLP | Deep Learning
Recent Activity
liked
a model
about 20 hours ago
sarvamai/sarvam-1
updated
a model
8 days ago
aastha6/work-llama-3.2-1b-instruct
published
a model
8 days ago
aastha6/work-llama-3.2-1b-instruct
Organizations
aastha6's activity
Facing error while converting to HF
1
#2 opened 3 months ago
by
aastha6
how to fine tune this model?
4
#16 opened 8 months ago
by
leo009
![](https://cdn-avatars.huggingface.co/v1/production/uploads/646334477e9025b09bd57d75/MDysdEWFWeJQDeDOLmdvI.png)
How to load in multi-gpu instance ?
6
#19 opened 8 months ago
by
aastha6
Cuda error for MAX_TOTAL_TOKENS = 8192
1
#5 opened over 1 year ago
by
aastha6
Trying to deploy this model with vllm in Sagemaker
#2 opened over 1 year ago
by
aastha6
Not able to launch using TGI in Sagemaker
#11 opened over 1 year ago
by
aastha6
Not able to deploy in Sagemaker
2
#3 opened over 1 year ago
by
aastha6
Code to shard a model weights
#1 opened over 1 year ago
by
aastha6