Views
No views yet
| Field | Details |
|---|---|
| Model Name | mjpsm/checkin-generator-distilgpt2 |
| Base Model | distilgpt2 |
| Task | Text Generation (Causal Language Modeling) |
| Training Data | ~20,000 cleaned student check-ins |
| Framework | Hugging Face Transformers |
| Use Case | Generate CIC-style check-ins from prompts |
Today i worked onToday i worked on making some progress on getting the authentication set up. It's been a bit of a struggle, but I think i'm finally starting to get the hang of itpip install transformers torch1from transformers import AutoTokenizer, AutoModelForCausalLM
2
3model_name = "mjpsm/checkin-generator-distilgpt2"
4tokenizer = AutoTokenizer.from_pretrained(model_name)
5model = AutoModelForCausalLM.from_pretrained(model_name)1import torch
2
3def generate(prompt, max_length=50):
4 inputs = tokenizer(prompt, return_tensors="pt")
5 outputs = model.generate(
6 inputs["input_ids"],
7 max_length=max_length,
8 do_sample=True,
9 top_k=50,
10 top_p=0.95,
11 temperature=0.8,
12 pad_token_id=tokenizer.eos_token_id
13 )
14 return tokenizer.decode(outputs[0], skip_special_tokens=True)
15
16print(generate("today i worked on"))