Azamorn
/

Meta-Llama-3-8B-Instruct-Distributed

Model card Files Files and versions Community

Azamorn commited on May 11

Commit

e07040b

•

1 Parent(s): 200a974

Update README.md

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -22,4 +22,8 @@ make main
 4. Run Distributed Llama:
 ```
 ./main inference --prompt "Hello world" --steps 128 --weights-float-type q40 --buffer-float-type q80 --nthreads 4 --model path/to/dllama_meta-llama-3-8b_q40.bin --tokenizer path/to/dllama_meta-llama3-tokenizer.t
-```

 4. Run Distributed Llama:
 ```
 ./main inference --prompt "Hello world" --steps 128 --weights-float-type q40 --buffer-float-type q80 --nthreads 4 --model path/to/dllama_meta-llama-3-8b_q40.bin --tokenizer path/to/dllama_meta-llama3-tokenizer.t
+```
+### Chat Template
+Please keep in mind this model expects the prompt to use the chat template of llama 3.