Request: Cran-May/T.E-8.1
#76
by
Cran-May
- opened
[Required] Model name:
Cran-May/T.E-8.1
[Required] Model link:
Cran-May/T.E-8.1
[Required] Brief description:
Trained for roleplay uses.
[Required] An image/direct image link to represent the model (square shaped):
[Optional] Additonal quants (if you want any):
Default list of quants for reference:
"IQ3_M", "IQ3_XXS",
"Q4_K_M", "Q4_K_S", "IQ4_XS",
"Q5_K_M", "Q5_K_S",
"Q6_K",
"Q8_0"
Will be uploaded in the evening. 😊
Having an issue that was supposed to already have been fixed with this Qwen 2.5 model:
issues/6419 | pull/6443
Seems to only affect Qwen.
Not sure if it was a regression, I'll check with the llama.cpp folks for a fix.
Apologies in advance.
The model's tokenizer is fixed now.
Uploaded at:
https://huggingface.co/Lewdiculous/T.E-8.1-GGUF-IQ-Imatrix-Request
What is expected Prompt format?
It should be ChatML as usual?
Lewdiculous
changed discussion status to
closed