Instructions to use krogoldAI/QueryRefiner-0.5B-v0.1-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use krogoldAI/QueryRefiner-0.5B-v0.1-GRPO with Transformers:

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

pipe = pipeline("text-generation", model="krogoldAI/QueryRefiner-0.5B-v0.1-GRPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("krogoldAI/QueryRefiner-0.5B-v0.1-GRPO")
model = AutoModelForCausalLM.from_pretrained("krogoldAI/QueryRefiner-0.5B-v0.1-GRPO", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use krogoldAI/QueryRefiner-0.5B-v0.1-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "krogoldAI/QueryRefiner-0.5B-v0.1-GRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "krogoldAI/QueryRefiner-0.5B-v0.1-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/krogoldAI/QueryRefiner-0.5B-v0.1-GRPO

SGLang

How to use krogoldAI/QueryRefiner-0.5B-v0.1-GRPO 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 "krogoldAI/QueryRefiner-0.5B-v0.1-GRPO" \
    --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": "krogoldAI/QueryRefiner-0.5B-v0.1-GRPO",
		"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 "krogoldAI/QueryRefiner-0.5B-v0.1-GRPO" \
        --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": "krogoldAI/QueryRefiner-0.5B-v0.1-GRPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use krogoldAI/QueryRefiner-0.5B-v0.1-GRPO with Docker Model Runner:
```
docker model run hf.co/krogoldAI/QueryRefiner-0.5B-v0.1-GRPO
```

krogoldAI commited on Oct 13, 2025

Commit

b55e6d9

verified ·

1 Parent(s): 0f22188

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -22

README.md CHANGED Viewed

@@ -337,7 +337,7 @@ messages = [
 input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 inputs = tokenizer(input_text, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=512)
 analysis = tokenizer.decode(outputs[0], skip_special_tokens=True)
 print(analysis)
@@ -345,8 +345,6 @@ print(analysis)
 ## Evaluation and Performance
-<!-- The model was trained on data that passed stringent quality thresholds, with all training examples achieving perfect structural conformance and semantic quality scores of 4 or higher across six evaluation dimensions: domain accuracy, intent accuracy, ambiguity assessment, rephrasing quality, intent preservation, and guideline adherence. This ensures the model learned from consistently high-quality demonstrations of the desired behavior. -->
 ### Structural Validation
 To assess the model's ability to produce correctly formatted outputs, we evaluated structural conformance across 1,000 examples from the test split of [krogoldAI/rag-ambiguous-queries](https://huggingface.co/datasets/krogoldAI/rag-ambiguous-queries), comparing both QueryRefiner-0.5B-v0.1 models against their base model [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct). The evaluation measured adherence to the required XML schema, including tag presence, well-formedness, element ordering, and confidence score formatting.
@@ -361,14 +359,6 @@ To assess the model's ability to produce correctly formatted outputs, we evaluat
 |Confidence|3.1%|99.9%|99.9%|
 |Perfectly structured output|0.0%|99.8%|99.9%|
-<!-- |Metric|Qwen2.5-0.5B-Instruct|QueryRefiner-0.5B-v0.1-SFT|QueryRefiner-0.5B-v0.1-GRPO-SFT|QueryRefiner-0.5B-v0.1-GRPO-SFT1-SFT2-v2|
-|----:|:-------------------:|:--------------------:|:--------------------:|:--------------------:|
-|Tag structure|10.8%|99.9%|100%|99.9%|
-|XML validity|41.0%|99.8%|99.8%|99.9%|
-|Order|2.0%|99.9%|100%|99.9%|
-|Confidence|3.1%|99.9%|100%|99.9%|
-|Perfectly structured output|0.0%|99.8%|99.8%|99.9%| -->
 Here, *tag structure* verifies that all required XML tags are present, *XML validity* ensures the output is well-formed and parseable, *order* confirms that required tags appear in the correct sequence, and *confidence* validates that confidence values are properly formatted and sum to `1.0`.
 <!-- The results demonstrate that fine-tuning substantially improved structural reliability, with QueryRefiner achieving near-perfect conformance (99.6%) compared to the base model's inability to produce any fully compliant outputs. -->
@@ -389,17 +379,6 @@ Beyond structural correctness, we evaluated the semantic quality of the model's
 |Follows guidelines|97.07 ± 13.78%|**97.40 ± 12.20%**|
 |Overall semantic score|96.10 ± 9.74%|**96.81 ± 9.18%**|
-<!-- |Metric|QueryRefiner-0.5B-v0.1-SFT|QueryRefiner-0.5B-v0.1-GRPO-SFT|QueryRefiner-0.5B-v0.1-GRPO-SFT1-SFT2-v2|
-|----:|:--------------------:|:--------------------:|:--------------------:|
-|Domain accuracy|**98.97 ± 8.43%**|98.57 ± 10.25%|98.95 ± 8.46%|
-|Intent accuracy|98.20 ± 8.84%|**98.85 ± 8.30%**|98.75 ± 8.05%|
-|Ambiguity assessment|99.04 ± 6.84%|99.10 ± 6.66%|**99.40 ± 5.79%**|
-|Rephrasing quality|88.23 ± 18.20%|89.60 ± 17.50%|**90.33 ± 17.61%**|
-|Intent preservation|95.09 ± 15.74%|95.52 ± 15.00%|**96.02 ± 14.72%**|
-|Follows guidelines|97.07 ± 13.78%|97.07 ± 12.90%|**97.40 ± 12.20%**|
-|Overall semantic score|96.10 ± 9.74%|96.45 ± 9.52%|**96.81 ± 9.18%**|
- -->
 All values are reported as mean ± standard deviation (%), computed over test examples. The base model produced too few valid XML samples for meaningful semantic evaluation.
 <details>

 input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 inputs = tokenizer(input_text, return_tensors="pt")
+outputs = model.generate(**inputs, temperature=0.7, max_new_tokens=512)
 analysis = tokenizer.decode(outputs[0], skip_special_tokens=True)
 print(analysis)
 ## Evaluation and Performance
 ### Structural Validation
 To assess the model's ability to produce correctly formatted outputs, we evaluated structural conformance across 1,000 examples from the test split of [krogoldAI/rag-ambiguous-queries](https://huggingface.co/datasets/krogoldAI/rag-ambiguous-queries), comparing both QueryRefiner-0.5B-v0.1 models against their base model [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct). The evaluation measured adherence to the required XML schema, including tag presence, well-formedness, element ordering, and confidence score formatting.
 |Confidence|3.1%|99.9%|99.9%|
 |Perfectly structured output|0.0%|99.8%|99.9%|
 Here, *tag structure* verifies that all required XML tags are present, *XML validity* ensures the output is well-formed and parseable, *order* confirms that required tags appear in the correct sequence, and *confidence* validates that confidence values are properly formatted and sum to `1.0`.
 <!-- The results demonstrate that fine-tuning substantially improved structural reliability, with QueryRefiner achieving near-perfect conformance (99.6%) compared to the base model's inability to produce any fully compliant outputs. -->
 |Follows guidelines|97.07 ± 13.78%|**97.40 ± 12.20%**|
 |Overall semantic score|96.10 ± 9.74%|**96.81 ± 9.18%**|
 All values are reported as mean ± standard deviation (%), computed over test examples. The base model produced too few valid XML samples for meaningful semantic evaluation.
 <details>