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 12, 2025

Commit

d9f7da7

verified ·

1 Parent(s): 751e4ae

Update README.md

Browse files

Files changed (1) hide show

README.md +24 -21

README.md CHANGED Viewed

@@ -37,22 +37,20 @@ Model output:
 ```xml
 <query_analysis>
   <domain ambiguous="true">
-    <candidate confidence="0.6">Biography</candidate>
-    <candidate confidence="0.4">Factual Information</candidate>
   </domain>
   <intent ambiguous="true">
-    <candidate confidence="0.7">Factual Question</candidate>
-    <candidate confidence="0.3">Interpretation</candidate>
   </intent>
   <concepts>
     <explicit>mother</explicit>
   </concepts>
-  <relations>
-    <relation subject="mother" predicate="height" object="[PERSON]"/>
-  </relations>
-  <insufficient_context>false</insufficient_context>
   <rephrased>true</rephrased>
-  <rephrased_query>Is [PERSON]'s mother tall?</rephrased_query>
 </query_analysis>
 ```
@@ -76,16 +74,16 @@ Model output:
     <candidate confidence="1.0">Data privacy and ethics</candidate>
   </intent>
   <concepts>
-    <explicit>data gathering, language models</explicit>
-    <implicit>legal considerations, ethical practices</implicit>
   </concepts>
   <relations>
     <relation subject="data gathering" predicate="must consider" object="legal aspects"/>
-    <relation subject="language models" predicate="require" object="legal considerations"/>
   </relations>
   <insufficient_context>false</insufficient_context>
   <rephrased>true</rephrased>
-  <rephrased_query>legal requirements for data collection and usage when developing natural language processing models</rephrased_query>
 </query_analysis>
 ```
@@ -96,27 +94,32 @@ Model output:
 User query:
-> How do they enhance its performance?
 Model output:
 ```xml
 <query_analysis>
   <domain ambiguous="true">
-    <candidate confidence="0.5">Technology</candidate>
-    <candidate confidence="0.5">Engineering</candidate>
   </domain>
   <intent ambiguous="true">
-    <candidate confidence="0.6">Performance enhancement</candidate>
-    <candidate confidence="0.4">Troubleshooting</candidate>
   </intent>
   <concepts>
-    <explicit>performance</explicit>
-    <implicit>[TECHNOLOGY/ENGINEERING] capabilities</implicit>
   </concepts>
   <insufficient_context>true</insufficient_context>
   <rephrased>true</rephrased>
-  <rephrased_query>how do [TECHNOLOGY/ENGINEERING] enhancements improve [PRODUCT/SERVICE] performance</rephrased_query>
 </query_analysis>
 ```

 ```xml
 <query_analysis>
   <domain ambiguous="true">
+    <candidate confidence="0.5">Biography</candidate>
+    <candidate confidence="0.5">History</candidate>
   </domain>
   <intent ambiguous="true">
+    <candidate confidence="0.6">Factual question</candidate>
+    <candidate confidence="0.4">Definition lookup</candidate>
   </intent>
   <concepts>
     <explicit>mother</explicit>
+    <implicit>[PERSON]</implicit>
   </concepts>
+  <insufficient_context>true</insufficient_context>
   <rephrased>true</rephrased>
+  <rephrased_query>Was [PERSON]'s mother tall?</rephrased_query>
 </query_analysis>
 ```
     <candidate confidence="1.0">Data privacy and ethics</candidate>
   </intent>
   <concepts>
+    <explicit>data gathering, language models, legal aspects</explicit>
+    <implicit>data protection, data governance, ethical considerations</implicit>
   </concepts>
   <relations>
     <relation subject="data gathering" predicate="must consider" object="legal aspects"/>
+    <relation subject="language models" predicate="trained on" object="data gathered"/>
   </relations>
   <insufficient_context>false</insufficient_context>
   <rephrased>true</rephrased>
+  <rephrased_query>legal requirements for collecting and protecting sensitive data when training natural language processing (NLP) models</rephrased_query>
 </query_analysis>
 ```
 User query:
+> How does she describe her emotional journey and the complexities of her interactions with him in that book?
 Model output:
 ```xml
 <query_analysis>
   <domain ambiguous="true">
+    <candidate confidence="0.5">Literature</candidate>
+    <candidate confidence="0.5">Psychology</candidate>
   </domain>
   <intent ambiguous="true">
+    <candidate confidence="0.6">Analysis</candidate>
+    <candidate confidence="0.4">Description</candidate>
   </intent>
   <concepts>
+    <explicit>emotional journey, interactions, book</explicit>
+    <implicit>[PERSON], complex</implicit>
   </concepts>
+  <relations>
+    <relation subject="[PERSON]" predicate="describe" object="emotional journey"/>
+    <relation subject="[PERSON]" predicate="interact with" object="him"/>
+    <relation subject="book" predicate="describe" object="[PERSON]'s journey and interactions"/>
+  </relations>
   <insufficient_context>true</insufficient_context>
   <rephrased>true</rephrased>
+  <rephrased_query>How does [PERSON] describe her emotional journey and the complexities of her interactions with [PERSON] in the book?</rephrased_query>
 </query_analysis>
 ```