How is this created
Thank you for the model, but can you describe process how was it created, if it is a merge then of what or datasets used for creation. It is based on mistral 7b or mistral 7b v.02? if you could describe other things like chat template it would be helpful thank you.
Hello @supercharge19 Thanks for your interest, this model is fully trained using new training method, we are working on a paper i will share after publishing it on arxiv (it may take a while), this is just a testing submission, hopefully you will see much better models soon )) stay tuned
Regarding chat template i will add it to the tokenizer in the next versions, sorry for inconvenience
Would love to see new technique, hope to see the paper soon, going to test the model now. Also congratulations on winning 7b model race (though leaderboard miscalculated and should be reranked).
@ammarali32 what happened? Where did the lazer model go? Though I think I tried that (quantized version) and it was very bad, it would not condemn zionists no matter what I ask it, genocide or raping innocent women and children in IDF captivity, model would just not criticize zionists would always try to escape by calling it allegations and not being able to form a judgement being just an AI model, yet would judge me pretty harshly if I say anything unwelcomed in modern "societies" or neo morphic cults of west.
@supercharge19
I removed it, it seems there is a bug somewhere with LASER.
Which quantized version ?
@ammarali32 I was using 4KM or 5KM, sorry I forgot whose implementation of quantization I was using.