Update README.md

README.md

@@ -9,7 +9,7 @@ license: apache-2.0
 # Model Card for Ostrich
 
 
-- **Trained with some of the Nostr notes**
+- **Trained with Nostr notes**
 - **Aligned a bit in these domains:**
 - Bitcoin
 - Health
@@ -18,12 +18,11 @@ license: apache-2.0
 - Alternative medicine
 - Herbs
 - Nutrition
+- Faith
 
-Read more about it here:
-https://habla.news/a/naddr1qvzqqqr4gupzp8lvwt2hnw42wu40nec7vw949ys4wgdvums0svs8yhktl8mhlpd3qqxnzde3xsunjwfkxcunwv3jvtnjyc
+You can read more about it here:
+https://habla.news/a/naddr1qvzqqqr4gupzp8lvwt2hnw42wu40nec7vw949ys4wgdvums0svs8yhktl8mhlpd3qqxnzde3xumrswfjx56rjwf4kkqhsx
 
-A running model is here:
-https://njump.me/npub1chadadwep45t4l7xx9z45p72xsxv7833zyy4tctdgh44lpc50nvsrjex2m   (Though it may be down for maintenance time to time. You need to DM the bot for it to answer.)
 
 
 ## Model Details
@@ -31,7 +30,7 @@ https://njump.me/npub1chadadwep45t4l7xx9z45p72xsxv7833zyy4tctdgh44lpc50nvsrjex2m
 
 - **Finetuned from model:** https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct
 
-The number in the filenames like 4750 means the version. Higher numbers are newer versions.
+The number in the filenames like 7314 means the version. 
 
 
 ## Uses
@@ -62,4 +61,4 @@ Information that aligns well with humanity is preferred.
 
 LLaMa-Factory is used to train on 2x3090! fsdp_qlora is the technique. 
 
-The Nostr training took ~140 hours for a dataset of ~67MB.
+The Nostr training took ~200 hours.