updates for 70b and gpu process monitor

Author: lessw2020

dist_run.py

@@ -58,6 +58,7 @@
 NAME_TO_DISTRIBUTION_AND_DTYPE = {
     "llama2-7b-chat": ("meta-llama/Llama-2-7b-chat-hf", torch.float16),
     "llama3": ("meta-llama/Meta-Llama-3-8B-Instruct", torch.bfloat16),
+    "llama3-70b": ("meta-llama/Meta-Llama-3-70B-Instruct", torch.bfloat16),
 }
 
 

torchchat/distributed/force_download.py

@@ -1,5 +1,5 @@
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
-model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
+# tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-70B-Instruct")
 print("Model weights and tokenizer downloaded")