pythia-6.9b
import transformers
import torch
model_id = "dvruette/oasst-pythia-6.9b-4000-steps"
tokenizer = transformers.AutoTokenizer.from_pretrained(model_id)
model = transformers.AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).cuda()
pipeline = transformers.pipeline(task="text-generation", model=model, tokenizer=tokenizer, device="cuda:0")
input_text = "<|prompter|>Write an emacs lisp function that asks user for input and stores it to a list `foo-list`<|endoftext|><|assistant|>"
pipeline(input_text, max_new_tokens=128)
| generated_text | : | < | prompter | >Write an emacs lisp function that asks user for input and stores it to a list `foo-list`< | endoftext | >< | assistant | >Sure, here’s an example of an emacs lisp function that prompts the user for input and stores it to a list:\n\n“`lisp\n(defun ask-for-input ()\n (interactive)\n (let ((input (read-from-string (prompt “Enter something: “)))\n (foo-list nil))\n (while input\n (push (string-to-number input) foo-list)\n (setq input (read-from-string (prompt “Enter something else: “)))\n foo-list))\n“`\n\nThis |
input_text = "How to make postgres docker container not to expose 5432 port?"
prompt_template = "<|prompter|>{}<|endoftext|><|assistant|>"
prompt = prompt_template.format(input_text)
pipeline(prompt, max_new_tokens=256)
| generated_text | : | < | prompter | >How to make postgres docker container not to expose 5432 port?< | endoftext | >< | assistant | >To prevent PostgreSQL from exposing the 5432 port, you can modify the container’s configuration file and add the following line to the “ports” section:\n\n”ports”: {\n “postgres”: “3306:3306”,\n}\n\nThis will prevent PostgreSQL from listening on the 5432 port, which is used by the default “postgres” user to connect to the database. |
input_text = """
Write Pydantic BaseModel classes that correspond to the following JSON
Request body (JSON)
prompt: string.
The input text to complete.
max_tokens: optional int (default = 100)
Maximum number of tokens to generate. A token represents about 4 characters for English texts. The total number of tokens (prompt + generated text) cannot exceed the model's maximum context length. It is of 2048 for GPT-J and 1024 for the other models.
If the prompt length is larger than the model's maximum context length, the beginning of the prompt is discarded.
stream: optional boolean (default = false)
If true, the output is streamed so that it is possible to display the result before the complete output is generated. Several JSON answers are output. Each answer is followed by two line feed characters.
"""
prompt_template = "<|prompter|>{}<|endoftext|><|assistant|>"
prompt = prompt_template.format(input_text)
pipeline(prompt, max_new_tokens=256)