Exception has occurred: JSONDecodeError
Expecting value: line 1 column 1 (char 0)

During handling of the above exception, another exception occurred:

During handling of the above exception, another exception occurred:

File "C:\Users\Lia\testing\test.py", line 28, in
res = simple_completion(prompt, length=Max, temp=temperature, top_p=top_probability, top_k=top_k, rep=rep)

I'm unable to extract step_383500.tar.zstd.

I have a pretty simple issue.

This type of this file is Express Zip File Compression but when I try to open it with said tool, it claims that the file is not supported. I tried searching up the file type and got nothing. How am I suppose to decompress this file.

Hi,

I am getting the following error from context_setting.completion API.
I have tried both basic and adv example but similar issue.

Any pointers on how to resolve this?

Thanks!

/usr/lib/python3.7/json/decoder.py in raw_decode(self, s, idx)
353 obj, end = self.scan_once(s, idx)
354 except StopIteration as err:
--> 355 raise JSONDecodeError("Expecting value", s, err.value) from None
356 return obj, end

JSONDecodeError: Expecting value: line 1 column 1 (char 0)

=================================================================

My code based on your example:

from gpt_j.Basic_api import simple_completion

In the prompt enter something you want to generate

prompt = "def perfect_square(num):"

Max length of completion

Max = 200

Temperature controls the creativity of the model

A low temperature means the model will take less changes when completing a prompt

A high temperature will make the model more creative

Both temperature and top probability must be a float

temperature = 0.6

top probability is an alternative way to control the randomness of the model

top_probability = 1.0

top_k is the number of top responses to return

This is the number of responses the model will return

top_k = 1

Rep is the number of times the model will repeat itself

This is the number of times the model will repeat itself when generating a response

rep = 0.216

Here you set query equal to the desired values

Note values higher that 512 tend to take more time to generate

res = context_setting.completion(prompt,
user=User,
bot=Bot,
max_tokens=max_tokens,
temperature=temperature,
top_p=top_probability,
top_k=top_k,
rep=repetition)

Finally we print the result

print(res)

Hello, I am creating a chatbot with this API. I was wondering how I can add a stop sequence so it doesn't keep on generating text after the response.

Thank you very much!

i'm new to python. can i use some help?

Can you update how to fix this issue?

I am working on GPT-J to generate prompts and I am unable to run the code.

During handling of the above exception, another exception occurred:

I am getting the following error when I tried running python basic_usage_template.py and python advanced_usage_template.py

Traceback (most recent call last):
  File "/hdd2/srinath/gpt-j/advanced_usage_template.py", line 58, in <module>
    response = context_setting.completion(prompt,
  File "/hdd2/srinath/anaconda3/envs/SD_Aug/lib/python3.10/site-packages/gpt_j/gptj_api.py", line 67, in completion
    self.response = generate(f"{self.new_prompt} {user}: {self.main_intention}", token_max_length=max_tokens, temperature=temperature, top_p=top_p, top_k=top_k, rep=rep)
  File "/hdd2/srinath/anaconda3/envs/SD_Aug/lib/python3.10/site-packages/gpt_j/Gptj.py", line 12, in generate
    result = URL.json()
  File "/hdd2/srinath/anaconda3/envs/SD_Aug/lib/python3.10/site-packages/requests/models.py", line 975, in json
    raise RequestsJSONDecodeError(e.msg, e.doc, e.pos)
requests.exceptions.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

My python version is 3.10.6

Getting an HTTP error: [WinError 10061] No connection could be made because the target machine actively refused it'

Has anyone else been suddenly getting this message? 'Sorry, the public API is limited to around 20 queries per every 30 minutes'

Could you open source the package? It would be nice for users to be able to make modifications to the package that can then later be pushed to the main. Thank you in advance!

I can see that you're making requests to "https://playground-api.forefront.link/" and it seems like this is not responding.

Is the language filter seen as necessary for this package?

Or would it be better to add an adjustable level, it just flagged "knife" for me.

hi, how can I train it with my own training data through gogle colab?