-
Notifications
You must be signed in to change notification settings - Fork 9.7k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update special token handling in conversion scripts for gpt2 derived tokenizers #3746
Conversation
Baichuan does conversion differently, I'll have to look a bit more into it |
Is there immediate need? Tests work for me (with an rather old download) without any change. |
Not really, I took a look and I think it's best to leave it as it is, since it seems to be working. |
I converted all the other models from this PR and the tokenizer tests pass, so it's probably good to go |
I am getting this error:
Before this PR the convert-mpt-hf-to-gguf.py script worked for me. I am running on Windows 10 in a conda env with python 3.10.13 |
You need to update your 'transformers' package to at least v4.34.0. |
* master: (350 commits) speculative : ensure draft and target model vocab matches (ggerganov#3812) llama : correctly report GGUFv3 format (ggerganov#3818) simple : fix batch handling (ggerganov#3803) cuda : improve text-generation and batched decoding performance (ggerganov#3776) server : do not release slot on image input (ggerganov#3798) batched-bench : print params at start log : disable pid in log filenames server : add parameter -tb N, --threads-batch N (ggerganov#3584) (ggerganov#3768) server : do not block system prompt update (ggerganov#3767) sync : ggml (conv ops + cuda MSVC fixes) (ggerganov#3765) cmake : add missed dependencies (ggerganov#3763) cuda : add batched cuBLAS GEMM for faster attention (ggerganov#3749) Add more tokenizer tests (ggerganov#3742) metal : handle ggml_scale for n%4 != 0 (close ggerganov#3754) Revert "make : add optional CUDA_NATIVE_ARCH (ggerganov#2482)" issues : separate bug and enhancement template + no default title (ggerganov#3748) Update special token handling in conversion scripts for gpt2 derived tokenizers (ggerganov#3746) llama : remove token functions with `context` args in favor of `model` (ggerganov#3720) Fix baichuan convert script not detecing model (ggerganov#3739) make : add optional CUDA_NATIVE_ARCH (ggerganov#2482) ...
It's not tested yet, I'll test it by updating #3742 later today
Change discussed in #3730