nvidia
/

nemo-megatron-gpt-20B

text generation

Model card Files Files and versions Community

okuchaiev commited on Sep 15, 2022

Commit

7dc7650

•

1 Parent(s): b3c6946

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -57,7 +57,7 @@ Alternatively, you can use NeMo Megatron training docker container with all depe
 git clone https://github.com/NVIDIA/NeMo.git
 cd NeMo/examples/nlp/language_modeling
 git checkout v1.11.0
-python megatron_gpt_eval.py gpt_model_file=nemo_gpt20B_fp16_tp8.nemo server=True tensor_model_parallel_size=2 trainer.devices=2
 ```
 ### Step 3: Send prompts to you model!

 git clone https://github.com/NVIDIA/NeMo.git
 cd NeMo/examples/nlp/language_modeling
 git checkout v1.11.0
+python megatron_gpt_eval.py gpt_model_file=nemo_gpt20B_bf16_tp8.nemo server=True tensor_model_parallel_size=2 trainer.devices=2
 ```
 ### Step 3: Send prompts to you model!