Regarding the use of models, even if it is a Gated model, you only need to obtain permission, and there are no fees. If it is a public model, you can load it without using tokens.
However, many people fall into pitfalls related to tokens.
Hello everyone,
im currently training LLMs locally with the Unsloth framework. After training they provide a way to upload your model to the Huggingface Hub.
model.push_to_hub_gguf(
“LuuWee/modelspacename”, # Change hf to your username!
tokenizer,
quantization_method = [“q4_k_m”, “q8_0”, “q5_k_m”,],
token = “hf_access_token”,
)
For it to upload you need to add your username and an Accesstoken in the request. This worked for me when i trained in Google Colab. I tried the same thing in my …
Hello!
The problem is: I’ve generated several tokens, but no one of them works=(
Errors are: API: Authorization header is correct, but the token seems invalid
Invalid token or no access to Hugging Face
I tried write-token, read-token, token with all permissions.
What am I doing wrong?
1 Like