Various levels of sharding on Meta's Llama 2 7B model for comparing effects of sharding.
Jason Weber
jasonweber99
AI & ML interests
None yet
Organizations
None yet
Collections
2
models
14
jasonweber99/Llama-2-7B-12gb-shards
Text Generation
•
Updated
•
1
jasonweber99/Llama-2-7B-4gb-shards
Text Generation
•
Updated
•
2
jasonweber99/Llama-3-8B-12gb-shards
Text Generation
•
Updated
jasonweber99/Llama-2-7B-1gb-shards
Text Generation
•
Updated
•
2
jasonweber99/Llama-2-7B-2gb-shards
Text Generation
•
Updated
•
2
jasonweber99/Llama-2-7B-8gb-shards
Text Generation
•
Updated
jasonweber99/Llama-3-8B-8gb-shards
Text Generation
•
Updated
jasonweber99/Llama-3-8B-4gb-shards
Text Generation
•
Updated
jasonweber99/Llama-3-8B-1gb-shards
Text Generation
•
Updated
jasonweber99/Llama-3-8B-2gb-shards
Text Generation
•
Updated
datasets
None public yet