when attempting to download/save model to run on replicate.com I get KeyError: 'llama'
I am following instructions on
https://replicate.com/docs/guides/push-a-transformers-model#intro
i have setup a huggingface access token and and get quite a bit into the process. But I finally get:
Token will not been saved to git credential helper. Pass add_to_git_credential=True if you want to set the git credential as well.
Token is valid (permission: read).
Your token has been saved to /root/.cache/huggingface/token
Login successful
config.json: 100%|
...
Traceback (most recent call last):
File "/src/script/download_weights", line 16, in
model = AutoModelForCausalLM.from_pretrained('epfl-llm/meditron-70b', cache_dir=CACHE_DIR)
File "/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 434, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 873, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/root/.pyenv/versions/3.10.13/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 579, in getitem
raise KeyError(key)
KeyError: 'llama'
ⅹ exit status 1
Any help welcome.