Instructions to use flax-community/mongolian-gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flax-community/mongolian-gpt2 with Transformers:

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

pipe = pipeline("text-generation", model="flax-community/mongolian-gpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flax-community/mongolian-gpt2")
model = AutoModelForCausalLM.from_pretrained("flax-community/mongolian-gpt2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use flax-community/mongolian-gpt2 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/flax-community/mongolian-gpt2

SGLang

How to use flax-community/mongolian-gpt2 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 "flax-community/mongolian-gpt2" \
    --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": "flax-community/mongolian-gpt2",
		"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 "flax-community/mongolian-gpt2" \
        --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": "flax-community/mongolian-gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flax-community/mongolian-gpt2 with Docker Model Runner:
```
docker model run hf.co/flax-community/mongolian-gpt2
```

Mongolian GPT2

Goal is to create a strong language generation model for Mongolian Since initial code and data is pretty much written by @patrickvonplaten and other huggingface members, it should not be so hard to get the first sense.

Model

Randomly initialized GPT2 model

Datasets

We can use OSCAR which is available through datasets

Datasets

A causal language modeling script for Flax is available here 1. It can be used pretty much without any required code changes. If there is time left, I’d love to try some private crawling and integrate it datasets.

Expected Outcome

Understandable Mongolian text generation model

Challenges

Lack of data → OSCAR Mongolian is just 2.2G. Maybe we need to research ways to acquire more data with this.

Downloads last month: 8

flax-community
/

mongolian-gpt2

Mongolian GPT2

Model

Datasets

Datasets

Expected Outcome

Challenges

Dataset used to train flax-community/mongolian-gpt2