Hugging Face's logo

vilsonrodrigues
/
falcon-7b-instruct-sharded

Text Generation
Transformers
Safetensors
English
falcon
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
8

How does one shards a model?

#6
by Oburaco - opened
Discussion
Oburaco

How does one shards a model?

vilsonrodrigues
 Owner

using

model.push_to_hub(REMOTE_PATH,
max_shard_size="2GB",
safe_serialization=True)

https://github.com/vilsonrodrigues/playing-with-falcon/blob/main/notebooks/fragmenting-falcon-7b-instruct.ipynb

vilsonrodrigues changed discussion status to closed

Sign up or log in to comment