Hugging Face's logo

TheBloke
/
CodeLlama-34B-GGUF

Text Generation
Transformers
GGUF
code
llama
llama-2
text-generation-inference
Model card Files Community
4

GGML support?

#1
by yigitbey - opened
Discussion
yigitbey

I love your speed! Will you release a ggml version of this model since llama.cpp considers GGUF support as beta?

TheBloke
 Owner

Yes coming shortly

deleted

@TheBloke Great to hear that.
And as always thanks for what you do for us

staviq

I'd recommend updating llamacpp and going with gguf, because any compatibility issues are being solved on gguf, and ggml is considered lower priority

mirek190

yep ggml versions are actually redundant (EOF)

deleted

yep ggml versions are actually redundant (EOF)

Well not yet, but soon.. Until everyone supports the new format, they are still of value.

Sign up or log in to comment