FriendliAI
/

Meta-Llama-3-70B-fp8

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions Community

yunmorning commited on Apr 22

Commit

1399254

•

1 Parent(s): e89e643

Update README.md

Files changed (1) hide show

README.md +0 -1

README.md CHANGED Viewed

@@ -271,7 +271,6 @@ docker run \
     --web-server-port 8000 \
     --hf-model-name FriendliAI/Meta-Llama-3-70B-fp8 \
     --num-devices 2  # Use tensor parallelism degree 2
 ```
 ---

     --web-server-port 8000 \
     --hf-model-name FriendliAI/Meta-Llama-3-70B-fp8 \
     --num-devices 2  # Use tensor parallelism degree 2
 ```
 ---