another models i made
https://huggingface.co/simonko912/chan-shitpost-2.5-llama-large
https://huggingface.co/simonko912/chan-shitpost-2.5-llama-small
basicly models trained on 4chan and other things (~1.7 million messages)
can be nsfw too, posted screenshots here (richard seen them i think)
https://x.com/simonko912/status/2033243433611960584
let's hope it works
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#chan-shitpost-2.5-llama-large-GGUF
https://hf.tst.eu/model#chan-shitpost-2.5-llama-small-GGUF
for quants to appear.
let's hope it works
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#chan-shitpost-2.5-llama-large-GGUF
https://hf.tst.eu/model#chan-shitpost-2.5-llama-small-GGUF
for quants to appear.
Great, gonna test them on my phone (I use pocket pall to run ggufs on my phone btw)
let's hope it works
You can check for progress at http://hf.tst.eu/status.html or regularly check the model
summary page at https://hf.tst.eu/model#chan-shitpost-2.5-llama-large-GGUF
https://hf.tst.eu/model#chan-shitpost-2.5-llama-small-GGUF
for quants to appear.
@RichardErkhov
So I just realized I was gaslighted by my coding ai with my training script so the model was fed plain text not JSONL ._.
skill issue
skill issue
then i relized it was okay, i just need to add start tokens and stop tokens ._.