If the 13 is not fixed, it should be a fine tune of qwen-14b, but there are almost none. There is also CausalLM-14b
I saw a conversation about that. It has been suggested that one has to change the tokenizer to make it fully compatible with the hf ecosystem, but I don't know how to do that.
https://preview.redd.it/xmxi4xev472c1.png?width=563&format=png&auto=webp&s=9e222fb39cc7ffb59937c1218a26a47b193e9475
https://preview.redd.it/1i07b2qy472c1.png?width=563&format=png&auto=webp&s=6e5c39b52b73da1f5814ef2a886c66ab93606cc2
If the 13 is not fixed, it should be a fine tune of qwen-14b, but there are almost none. There is also CausalLM-14b