Update README.md

README.md

@@ -10,8 +10,8 @@ license: apache-2.0
 
 
 - **Trained with some of the Nostr notes**
-- **Likes to disagree more compared to Llama3. It can be used for refutation, counter argument production.**
 - **Aligned a bit in these domains:**
+- Bitcoin
 - Health
 - Permaculture
 - Phytochemicals
@@ -22,6 +22,10 @@ license: apache-2.0
 Read more about it here:
 https://habla.news/a/naddr1qvzqqqr4gupzp8lvwt2hnw42wu40nec7vw949ys4wgdvums0svs8yhktl8mhlpd3qqxnzde3xsunjwfkxcunwv3jvtnjyc
 
+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
 
 
@@ -32,11 +36,11 @@ The number in the filenames like 4750 means the version. Higher numbers are newe
 
 ## Uses
 
+Likes to disagree more compared to Llama3. It can be used for refutation, counter argument production.
+
 Ask any question, compared to other models this may know more about Nostr and Bitcoin.
-You can use llama.cpp to chat with it.
-You can also use llama-cpp-python package to use it in a Python script.
 
-Llama3 chat template can be used. <|begin_of_text|><|start_header_id|> ...
+You can use llama.cpp to chat with it. You can also use llama-cpp-python package to use it in a Python script.
 
 Use repeat penalty of 1.05 or more to avoid repetitions.
 
@@ -58,4 +62,4 @@ 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 ~30 hours for a dataset of about 20MB.
+The Nostr training took ~140 hours for a dataset of ~67MB.