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)

# 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
```

tokhey commited on Nov 27, 2025

Commit

5b0b331

verified ·

1 Parent(s): cbebcc9

Training in progress, step 160

Browse files

Files changed (2) hide show

adapter_model.safetensors +1 -1
trainer_log.jsonl +8 -0

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2832e178fbfc4fe2fb481e79a8d919fe407032c53cea12f332a1381234b6f1c4
 size 140815952

 version https://git-lfs.github.com/spec/v1
+oid sha256:4d364eb38a8be050b253d95fb9bb96a3cca85c934f5694fdf28af039b0f831af
 size 140815952

trainer_log.jsonl CHANGED Viewed

@@ -23,3 +23,11 @@
 {"current_steps": 110, "total_steps": 225, "loss": 0.4784, "lr": 0.0003077940805287425, "epoch": 1.4666666666666668, "percentage": 48.89, "elapsed_time": "0:58:34", "remaining_time": "1:01:14"}
 {"current_steps": 115, "total_steps": 225, "loss": 0.4422, "lr": 0.00028872454505352117, "epoch": 1.5333333333333332, "percentage": 51.11, "elapsed_time": "1:01:13", "remaining_time": "0:58:33"}
 {"current_steps": 120, "total_steps": 225, "loss": 0.4828, "lr": 0.0002694209618222516, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "1:03:51", "remaining_time": "0:55:52"}

 {"current_steps": 110, "total_steps": 225, "loss": 0.4784, "lr": 0.0003077940805287425, "epoch": 1.4666666666666668, "percentage": 48.89, "elapsed_time": "0:58:34", "remaining_time": "1:01:14"}
 {"current_steps": 115, "total_steps": 225, "loss": 0.4422, "lr": 0.00028872454505352117, "epoch": 1.5333333333333332, "percentage": 51.11, "elapsed_time": "1:01:13", "remaining_time": "0:58:33"}
 {"current_steps": 120, "total_steps": 225, "loss": 0.4828, "lr": 0.0002694209618222516, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "1:03:51", "remaining_time": "0:55:52"}
+{"current_steps": 125, "total_steps": 225, "loss": 0.4853, "lr": 0.00025, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "1:06:42", "remaining_time": "0:53:21"}
+{"current_steps": 130, "total_steps": 225, "loss": 0.4392, "lr": 0.00023057903817774841, "epoch": 1.7333333333333334, "percentage": 57.78, "elapsed_time": "1:09:21", "remaining_time": "0:50:40"}
+{"current_steps": 135, "total_steps": 225, "loss": 0.4489, "lr": 0.00021127545494647882, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "1:11:59", "remaining_time": "0:47:59"}
+{"current_steps": 140, "total_steps": 225, "loss": 0.4856, "lr": 0.00019220591947125766, "epoch": 1.8666666666666667, "percentage": 62.22, "elapsed_time": "1:14:37", "remaining_time": "0:45:18"}
+{"current_steps": 145, "total_steps": 225, "loss": 0.4406, "lr": 0.0001734856863530282, "epoch": 1.9333333333333333, "percentage": 64.44, "elapsed_time": "1:17:15", "remaining_time": "0:42:37"}
+{"current_steps": 150, "total_steps": 225, "loss": 0.4405, "lr": 0.0001552278990399052, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:19:53", "remaining_time": "0:39:56"}
+{"current_steps": 155, "total_steps": 225, "loss": 0.3784, "lr": 0.00013754290599809105, "epoch": 2.066666666666667, "percentage": 68.89, "elapsed_time": "1:22:32", "remaining_time": "0:37:16"}
+{"current_steps": 160, "total_steps": 225, "loss": 0.4102, "lr": 0.00012053759377541865, "epoch": 2.1333333333333333, "percentage": 71.11, "elapsed_time": "1:25:10", "remaining_time": "0:34:36"}