Collection of quantized Llama 3.1 models (8B & 70B versions for now), using bitsandbites.
Farid Saud
fsaudm
AI & ML interests
None yet
Recent Activity
New activity
about 2 months ago
nvidia/Llama-3.1-Nemotron-70B-Instruct:Model Config Error on VLLM?
Organizations
Collections
1
models
5
fsaudm/Meta-Llama-3.1-70B-Instruct-NF4
Text Generation
•
Updated
•
381
fsaudm/Meta-Llama-3.1-8B-Instruct-NF4
Text Generation
•
Updated
•
374
fsaudm/Reflection-Llama-3.1-70B-Instruct-NF4
Text Generation
•
Updated
•
12
fsaudm/Meta-Llama-3.1-8B-Instruct-INT8
Text Generation
•
Updated
•
51
fsaudm/Meta-Llama-3.1-70B-Instruct-INT8
Text Generation
•
Updated
•
568
datasets
None public yet