Instructions to use harpertoken/harpertokenConvFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use harpertoken/harpertokenConvFT with Transformers:

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

pipe = pipeline("text-generation", model="harpertoken/harpertokenConvFT")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("harpertoken/harpertokenConvFT")
model = AutoModelForCausalLM.from_pretrained("harpertoken/harpertokenConvFT")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use harpertoken/harpertokenConvFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/harpertoken/harpertokenConvFT

SGLang

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

Docker Model Runner
How to use harpertoken/harpertokenConvFT with Docker Model Runner:
```
docker model run hf.co/harpertoken/harpertokenConvFT
```

harpertokenConvFT

Commit History

Update README.md

0465329
verified

harpertoken commited on Sep 27, 2025

Update README.md

f824027
verified

harpertoken commited on Sep 27, 2025

Add Related Models and Model Differences sections for truthful discussion

7999200

bniladridas commited on Sep 15, 2025

Correct README: update base model to gpt2 and max sequence length to 1024

19d9673

bniladridas commited on Sep 15, 2025

Restore missing model files from initial commit

7643100

bniladridas commited on Sep 15, 2025

Adding `safetensors` variant of this model (#1)

1dd2b48
verified

harpertoken

SFconvertbot commited on Sep 15, 2025