davidkim205
/

komt-llama-30b-v1-lora

Text Generation

Model card Files Files and versions Community

davidkim205 commited on Oct 20, 2023

Commit

7df61eb

•

1 Parent(s): 4320b80

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ This study addresses these challenges by introducing a multi-task instruction te
 * **Model Developers** :  davidkim(changyeon kim)
 * **Repository** : https://github.com/davidkim205/komt
 * **Lora target modules** : q_proj, o_proj, v_proj, gate_proj, down_proj, k_proj, up_proj
-* **Model Size** : 80MB
 * **Model Architecture** : komt-llama-2-30b is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning by multi-task instruction
 ## Dataset
 korean multi-task instruction dataset

 * **Model Developers** :  davidkim(changyeon kim)
 * **Repository** : https://github.com/davidkim205/komt
 * **Lora target modules** : q_proj, o_proj, v_proj, gate_proj, down_proj, k_proj, up_proj
+* **Model Size** : 244MB
 * **Model Architecture** : komt-llama-2-30b is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning by multi-task instruction
 ## Dataset
 korean multi-task instruction dataset