Hugging Face's logo

ibm-research
/
PowerMoE-3b

Text Generation
Transformers
Safetensors
granitemoe
Eval Results
Model card Files Community
2
mayank-mishra commited on
Commit
6208e73
·
verified ·
1 Parent(s): 8b152ee

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -130,7 +130,7 @@ This is a simple example of how to use **PowerMoE-3b** model.
130
  import torch
131
  from transformers import AutoModelForCausalLM, AutoTokenizer
132
  device = "cuda" # or "cpu"
133
- model_path = "ibm/PowerLM-3b"
134
  tokenizer = AutoTokenizer.from_pretrained(model_path)
135
  # drop device_map if running on CPU
136
  model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
 
130
  import torch
131
  from transformers import AutoModelForCausalLM, AutoTokenizer
132
  device = "cuda" # or "cpu"
133
+ model_path = "ibm/PowerMoE-3b"
134
  tokenizer = AutoTokenizer.from_pretrained(model_path)
135
  # drop device_map if running on CPU
136
  model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)