Acknowledgement
#1
by
syubraj
- opened
First of all thank you for creating gguf file for the model I have been working on. However, I cannot be able to run it locally, although I have created a model pulling gguf file and using ollama.
The error says: "missing result_output tensor"
The model might simply be broken, or not supported by llama.cpp
Which one do you suggest then to make the model running? or would you check from your side, if possible.
works fine for me in llama.cpp (to the extend I can test it, my nepali is notoriosuly bad :)
$ llama-cli -m RomanEng2Nep-v2.Q4_K_S.gguf -p muskuraudai
कुंजलिसहित [end of text]
mradermacher
changed discussion status to
closed