Instructions to use Kongfha/PhraAphaiManee-LM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kongfha/PhraAphaiManee-LM with Transformers:

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

pipe = pipeline("text-generation", model="Kongfha/PhraAphaiManee-LM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kongfha/PhraAphaiManee-LM")
model = AutoModelForCausalLM.from_pretrained("Kongfha/PhraAphaiManee-LM")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kongfha/PhraAphaiManee-LM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Kongfha/PhraAphaiManee-LM

SGLang

How to use Kongfha/PhraAphaiManee-LM 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 "Kongfha/PhraAphaiManee-LM" \
    --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": "Kongfha/PhraAphaiManee-LM",
		"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 "Kongfha/PhraAphaiManee-LM" \
        --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": "Kongfha/PhraAphaiManee-LM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kongfha/PhraAphaiManee-LM with Docker Model Runner:
```
docker model run hf.co/Kongfha/PhraAphaiManee-LM
```

PhraAphaiManee-LM (แต่งกลอนสไตล์พระอภัยมณี ด้วย GPT-2)

** I've created an improved model with better performance, and you can now access it through this link -> Kongfha/KlonSuphap-LM **

PhraAphaiManee-LM or GPT-2 for Thai poem (PhraAphaiManee-Style). I use GPT-2 for Thai lyrics, which is based on GPT-2 base Thai as a pre-trained model for PhraAphaiManee (พระอภัยมณี) dataset.

*ตอนนี้ ผมได้ทำโมเดลใหม่ที่สามารถสัมผัสได้ดีกว่าแล้ว สามารถเข้าถึงได้จากลิงก์นี้ -> Kongfha/KlonSuphap-LM*
โมเดลนี้เป็น GPT-2 ถูกเทรนด้วยกลอนพระอภัยมณี สำหรับการแต่งกลอนสไตล์พระอภัยมณี

Example use

from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "Kongfha/PhraAphaiManee-LM"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

generate = pipeline("text-generation",
                    model=model,
                    tokenizer=tokenizer)

input_sentence = "๏ สัมผัสเส้นขอบฟ้าชลาลัย"
generated_text = generate(input_sentence,
                          max_length=140,
                          top_k=25,
                          temperature=1)
# generation parameters can be varied 

print(f"Input: {text}")
print(f"Output:\n {generated_text[0]['generated_text']}")

Downloads last month: 11

Safetensors

Model size

0.1B params

Tensor type

F32

BOOL

Kongfha
/

PhraAphaiManee-LM

PhraAphaiManee-LM (แต่งกลอนสไตล์พระอภัยมณี ด้วย GPT-2)

Example use

Space using Kongfha/PhraAphaiManee-LM 1