Update README.md

README.md

@@ -6,7 +6,7 @@ tags:
 - gpt-neox
 - KoAlpaca
 model-index:
-- name: KoAlpaca-Polyglot-12.8B
+- name: KoAlpaca-Polyglot-5.8B
   results: []
 language:
 - ko
@@ -16,11 +16,9 @@ pipeline_tag: text-generation
 ---
 
 
-# KoAlpaca-Polyglot-12.8B (v1.1b)
+# KoAlpaca-Polyglot-5.8B (v1.1b)
 
-This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on a KoAlpaca Dataset v1.1b
-
-Detail Codes are available at [KoAlpaca Github Repository](https://github.com/Beomi/KoAlpaca)
+This model is a fine-tuned version of [EleutherAI/polyglot-ko-5.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on a KoAlpaca Dataset v1.1b
 
 
 ## Training procedure
@@ -31,8 +29,8 @@ The following hyperparameters were used during training:
 - learning_rate: 5e-05
 - train_batch_size: 1
 - seed: 42
-- distributed_type: multi-GPU (A100 80G)
-- num_devices: 4
+- distributed_type: multi-GPU (A40 40G)
+- num_devices: 8
 - gradient_accumulation_steps: 64
 - total_train_batch_size: 256
 - total_eval_batch_size: 32