Basic chat using this model - first trial
Hi, thank you for uncesoring models, it is what I need to have fair outputs for my apps
I'm new to HuggingFace. I created basic application based on templates
Next step was to change the model, I was thinking that I will be succesfull just with this only change
but now prompt gives just error after first querry
What is the difference that just switching the models didnt gave the effect?
In the logs :
To create a public link, set share=True in launch().
Set as non chat completion Orenguteng/Llama-3-8B-Lexi-Uncensored
Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py", line 304, in hf_raise_for_status
response.raise_for_status()
File "/usr/local/lib/python3.10/site-packages/requests/models.py", line 1021, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 403 Client Error: Forbidden for url: https://api-inference.huggingface.co/models/Orenguteng/Llama-3-8B-Lexi-Uncensored/v1/chat/completions
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 556, in chat_completion
data = self.post(
File "/usr/local/lib/python3.10/site-packages/huggingface_hub/inference/_client.py", line 267, in post
hf_raise_for_status(response)
File "/usr/local/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py", line 367, in hf_raise_for_status
raise HfHubHTTPError(message, response=response) from e
huggingface_hub.utils._errors.HfHubHTTPError: (Request ID: p9_lGS_y29L3zoIVKrkeV)
403 Forbidden: None.
Cannot access content at: https://api-inference.huggingface.co/models/Orenguteng/Llama-3-8B-Lexi-Uncensored/v1/chat/completions.
If you are trying to create or update content,make sure you have a token with the write role.
The model Orenguteng/Llama-3-8B-Lexi-Uncensored is too large to be loaded automatically (17GB > 10GB). Please use Spaces (https://huggingface.co/spaces) or Inference Endpoints (https://huggingface.co/inference-endpoints).
I'm not sure is model is just to big, or I'am using wrong categories during replcement (apples vs oranges) or something else
I will be very gratefull for hints
I'm not sure , it seems that you are trying to run chat completions , inference on the model but this model is not hosted to run inference with on HF, it's just the model files, you need to download them and run them yourself.