tripathysagar/odia-gpt

Model Card for Model ID

Model Details

Model Description

This is the model card of a model trained by Karpathy's nanoGPT. The vocabulary size is 20_000 and the context window is 1024.
The model is trined on tripathysagar/odia-news, news paper article extracted from odia daily Dharitri.

Uses

>>> from huggingface_hub import snapshot_download
>>> snapshot_download(repo_id="tripathysagar/odia-gpt", local_dir='.')

>>> from model import GPT
>>> import os, torch

>>> from tokenizers import Tokenizer
>>> tokenizer = Tokenizer.from_file('tokenizer.json')
>>> nn, _ = GPT.from_file(os.path.join('model.pt'))
>>> nn = nn.to('cuda')

>>> s = 'କ୍ରେଡିଟ କାର୍ଡ ନେବା ସମୟରେ ଏହାର ସର୍ତ୍ତ ଏବଂ ନିୟମଗୁଡ଼ିକୁ ଧ୍ୟାନର ସହିତ ପଢ଼ିବା ଉଚିତ ।'
>>> enc = torch.tensor(tokenizer.encode(s).ids).unsqueeze(0).to('cuda')

>>> op = nn.generate(enc, 50, top_k=50)

>>> print(tokenizer.decode(op[0].to('cpu').tolist()))

Direct Use

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary