Nvidia Nemotron 253b gguf
#1
by
kkk0000
- opened
🥲 Failed to load the model
Failed to load model
error loading model: missing tensor 'blk.9.ffn_norm.weight'
Use this branch:
https://github.com/ggml-org/llama.cpp/pull/12843
(though I think is has just merged to llama.cpp master)
LMK if you experience issue with the branch above ^
kkk0000
changed discussion title from
Nvidia Nemotron 263b gguf
to Nvidia Nemotron 253b gguf
Is not worth the trouble. Thanks anyway.
kkk0000
changed discussion status to
closed
Is not worth the trouble. Thanks anyway.
blk.9.ffn_norm.weight is not in the gguf. You need the new code to skip reading this weight. Please make sure you compile llama.cpp from the PR or https://github.com/ymcki/llama.cpp and run llama-cli.