Instructions to use dehanalkautsar/gpt2-ne-wikimulti with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dehanalkautsar/gpt2-ne-wikimulti with Transformers:

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

pipe = pipeline("text-generation", model="dehanalkautsar/gpt2-ne-wikimulti")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dehanalkautsar/gpt2-ne-wikimulti")
model = AutoModelForCausalLM.from_pretrained("dehanalkautsar/gpt2-ne-wikimulti", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dehanalkautsar/gpt2-ne-wikimulti with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dehanalkautsar/gpt2-ne-wikimulti"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dehanalkautsar/gpt2-ne-wikimulti",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/dehanalkautsar/gpt2-ne-wikimulti

SGLang

How to use dehanalkautsar/gpt2-ne-wikimulti 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 "dehanalkautsar/gpt2-ne-wikimulti" \
    --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": "dehanalkautsar/gpt2-ne-wikimulti",
		"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 "dehanalkautsar/gpt2-ne-wikimulti" \
        --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": "dehanalkautsar/gpt2-ne-wikimulti",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use dehanalkautsar/gpt2-ne-wikimulti with Docker Model Runner:
```
docker model run hf.co/dehanalkautsar/gpt2-ne-wikimulti
```

GPT-2 Nepali WikiMulti

GPT-2-small model pretrained from scratch on the Nepali portion of WikiMulti.

Dataset

Dataset: dehanalkautsar/WikiMulti
File: 20260801_ne_wiki.parquet
Training field: text

Architecture

Standard GPT-2-small architecture:

Layers: 12
Hidden size: 768
Attention heads: 12
Maximum context: 1024
Vocabulary size: 43846

All GPT-2 weights were initialized from scratch.

No pretrained GPT-2 model weights were used.

Tokenizer

A separate Byte-Level BPE tokenizer was trained from scratch using only the Nepali training split.

The original English GPT-2 vocabulary and BPE merge rules were not used.

Vocabulary size: 43846

Training

GPU: NVIDIA RTX A6000
Precision: FP16
TF32: True
Maximum epochs: 50
Batch size per GPU: 8
Gradient accumulation: 4
Sequence length: 1024
Learning rate: 5e-05
Scheduler: linear
Validation frequency: every 500 optimizer steps
Early stopping patience: 999
Early stopping threshold: 0.0
Random seed: 42

Training was stopped after validation loss failed to improve for 999 consecutive evaluation rounds, unless the maximum epoch ceiling was reached first.

Best Model

Best validation loss:

1.5498346090316772

Final best-model validation loss:

1.5498346090316772

Perplexity:

4.71069101241065

Downloads last month: 964

Safetensors

Model size

0.1B params

Tensor type

F32