Instructions to use utsabdahal34/NepaliGPT-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use utsabdahal34/NepaliGPT-base with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="utsabdahal34/NepaliGPT-base")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("utsabdahal34/NepaliGPT-base")
model = AutoModelForCausalLM.from_pretrained("utsabdahal34/NepaliGPT-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use utsabdahal34/NepaliGPT-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "utsabdahal34/NepaliGPT-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "utsabdahal34/NepaliGPT-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/utsabdahal34/NepaliGPT-base

SGLang

How to use utsabdahal34/NepaliGPT-base with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "utsabdahal34/NepaliGPT-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "utsabdahal34/NepaliGPT-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "utsabdahal34/NepaliGPT-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "utsabdahal34/NepaliGPT-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use utsabdahal34/NepaliGPT-base with Docker Model Runner:
```
docker model run hf.co/utsabdahal34/NepaliGPT-base
```

utsabdahal34/NepaliGPT-base

NepaliGPT decoder-only model exported as standard Transformers GPT-2 weights. Install transformers, sentencepiece, torch, and huggingface_hub for the example below. The additional native model.pt requires the source package from https://github.com/utsab345/Nepali_GPT2.

Usage

from huggingface_hub import hf_hub_download
import sentencepiece as spm
import torch
from transformers import AutoModelForCausalLM

repo = "utsabdahal34/NepaliGPT-base"
tokenizer = spm.SentencePieceProcessor(model_file=hf_hub_download(repo, "tokenizer.model"))
model = AutoModelForCausalLM.from_pretrained(repo)
ids = torch.tensor([[tokenizer.bos_id()] + tokenizer.encode("नेपाल एक सुन्दर")])
output = model.generate(ids, max_new_tokens=40, do_sample=False)
print(tokenizer.decode(output[0].tolist()))

For an instruction-tuned checkpoint, construct the prompt with nepali_gpt2.sft.format_prompt(instruction, context).

Architecture

{
  "vocab_size": 16000,
  "context_length": 512,
  "emb_dim": 512,
  "n_heads": 8,
  "n_layers": 8,
  "drop_rate": 0.1,
  "qkv_bias": false
}

Data

Nepali Wikipedia and OSCAR Nepali are described in the source Colab notebook. The raw corpus and held-out split are not included in this export; verify upstream licenses before redistribution.

Training

Base checkpoint supplied by the project owner from the Colab notebook. Architecture is GPT-2 style with 16,000 SentencePiece tokens, 512 context, 512 hidden width, 8 layers and 8 heads. The exported checkpoint does not contain optimizer state or independently verifiable training-step metadata.

Evaluation

The supplied base checkpoint scores 3/5 on the repository cloze smoke set. Full generation and CPU benchmark reports are stored in docs/measurements when available. This score is not a broad quality benchmark.

Limitations

This is a base language model, not instruction tuned. It may repeat text, hallucinate facts and reflect source-data bias. Held-out perplexity, multilingual baseline, human instruction-following scores and CUDA measurements are unavailable in this export.

Downloads last month: 292

Safetensors

Model size

33.7M params

Tensor type

F32