Aastha Varma's picture

8 8 86

Aastha Varma

aastha6

·

https://medium.com/@aastha.code

AI & ML interests

Mechanistic Interpretability

Recent Activity

updated a model about 4 hours ago

aastha6/crosscoders-gemma-2-2b

published a model about 4 hours ago

aastha6/crosscoders-gemma-2-2b

updated a dataset 1 day ago

aastha6/pile-lmsys-mix-500k-tokenized-qwen2.5

View all activity

Organizations

aastha6's activity

New activity in meta-llama/Llama-3.2-1B-Instruct-QLORA_INT4_EO8 4 months ago

Facing error while converting to HF

#2 opened 4 months ago by

New activity in mistralai/Codestral-22B-v0.1 8 months ago

how to fine tune this model?

#16 opened 9 months ago by

New activity in mistralai/Codestral-22B-v0.1 9 months ago

How to load in multi-gpu instance ?

#19 opened 9 months ago by

New activity in TheBloke/Mistral-7B-Instruct-v0.1-GPTQ over 1 year ago

Cuda error for MAX_TOTAL_TOKENS = 8192

#5 opened over 1 year ago by

New activity in amazon/FalconLite2 over 1 year ago

Trying to deploy this model with vllm in Sagemaker

#2 opened over 1 year ago by

New activity in Open-Orca/Mistral-7B-OpenOrca over 1 year ago

Not able to launch using TGI in Sagemaker

#11 opened over 1 year ago by

New activity in michaelfeil/ct2fast-flan-ul2 over 1 year ago

Not able to deploy in Sagemaker

#3 opened over 1 year ago by

New activity in philschmid/gpt-j-6B-fp16-sharded over 1 year ago

Code to shard a model weights

#1 opened over 1 year ago by