Instructions to use ticoAg/gpt2-tigerbot-pt-zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ticoAg/gpt2-tigerbot-pt-zh with Transformers:

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

pipe = pipeline("text-generation", model="ticoAg/gpt2-tigerbot-pt-zh")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ticoAg/gpt2-tigerbot-pt-zh")
model = AutoModelForCausalLM.from_pretrained("ticoAg/gpt2-tigerbot-pt-zh")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ticoAg/gpt2-tigerbot-pt-zh with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ticoAg/gpt2-tigerbot-pt-zh

SGLang

How to use ticoAg/gpt2-tigerbot-pt-zh 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 "ticoAg/gpt2-tigerbot-pt-zh" \
    --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": "ticoAg/gpt2-tigerbot-pt-zh",
		"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 "ticoAg/gpt2-tigerbot-pt-zh" \
        --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": "ticoAg/gpt2-tigerbot-pt-zh",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ticoAg/gpt2-tigerbot-pt-zh with Docker Model Runner:
```
docker model run hf.co/ticoAg/gpt2-tigerbot-pt-zh
```

based gpt2

trained with LLaMA-Efficient-Tuning

python src/train_bash.py \
    --stage pt \
    --model_name_or_path gpt2 \
    --do_train \
    --finetuning_type full \
    --dataset tiger_pretrain_zh \
    --template ziya \
    --use_fast_tokenizer \
    --preprocessing_num_workers 64 \
    --per_device_train_batch_size 8 \
    --gradient_accumulation_steps 16 \
    --output_dir .cache/gpt2-tigerResearch_pretrain_zh \
    --lr_scheduler_type cosine \
    --logging_steps 10 \
    --save_steps 1000 \
    --eval_steps 500 \
    --learning_rate 5e-5 \
    --num_train_epochs 1.0 \
    --val_size 3000 \
    --evaluation_strategy steps \
    --plot_loss \
    --max_source_length 1024 \
    --bf16

Downloads last month: 5

ticoAg
/

gpt2-tigerbot-pt-zh

Dataset used to train ticoAg/gpt2-tigerbot-pt-zh