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

Libraries

How to use tokhey/question_generation_model with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "tokhey/question_generation_model")

Transformers

How to use tokhey/question_generation_model with Transformers:

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

pipe = pipeline("text-generation", model="tokhey/question_generation_model")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tokhey/question_generation_model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tokhey/question_generation_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tokhey/question_generation_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tokhey/question_generation_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tokhey/question_generation_model

SGLang

How to use tokhey/question_generation_model 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 "tokhey/question_generation_model" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tokhey/question_generation_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "tokhey/question_generation_model" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tokhey/question_generation_model",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

question_generation_model / README.md

tokhey

End of training

d3933ff verified 10 months ago

preview code

Raw History Blame Contribute Delete

1.71 kB

metadata

library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-0.5B-Instruct
tags:
  - base_model:adapter:Qwen/Qwen2.5-0.5B-Instruct
  - llama-factory
  - lora
  - transformers
pipeline_tag: text-generation
model-index:
  - name: question_generation_model
    results: []

question_generation_model

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the questions_finetune_train dataset. It achieves the following results on the evaluation set:

Loss: 0.5050

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0005
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.4919	1.3333	100	0.5065
0.3998	2.6667	200	0.5052

Framework versions

PEFT 0.17.1
Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 2.16.1
Tokenizers 0.22.1