Tijmen2
/

cosmosage_v2

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Tijmen2 commited on Feb 19

Commit

de9a5f8

•

1 Parent(s): f956cfe

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -57,7 +57,7 @@ textbooks, rather than just on synthetically generated QA pairs. However, it con
 _reliability_. While many of its answers are factually accurate, some are not. The outputs of cosmosage
 (or any LLM) should not be trusted to be factual.
-### Training details
 cosmosage_v2 was trained on 4xA100 (80 GB) at the Center for Computational Astrophysics (CfCA), National Astronomical Observatory of Japan (NAOJ).
@@ -85,7 +85,7 @@ The following hyperparameters were used during QA tuning:
 - num_epochs: 2.0
 - weight_decay: 0.0
-### Examples
 **User:**
 > What is Digital Active Nulling?

 _reliability_. While many of its answers are factually accurate, some are not. The outputs of cosmosage
 (or any LLM) should not be trusted to be factual.
+## Training details
 cosmosage_v2 was trained on 4xA100 (80 GB) at the Center for Computational Astrophysics (CfCA), National Astronomical Observatory of Japan (NAOJ).
 - num_epochs: 2.0
 - weight_decay: 0.0
+## Example output
 **User:**
 > What is Digital Active Nulling?