Instructions to use sheryc/Qwen2.5-7B-Instruct-CARE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sheryc/Qwen2.5-7B-Instruct-CARE with Transformers:

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

pipe = pipeline("text-generation", model="sheryc/Qwen2.5-7B-Instruct-CARE")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sheryc/Qwen2.5-7B-Instruct-CARE")
model = AutoModelForCausalLM.from_pretrained("sheryc/Qwen2.5-7B-Instruct-CARE")
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

vLLM

How to use sheryc/Qwen2.5-7B-Instruct-CARE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sheryc/Qwen2.5-7B-Instruct-CARE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sheryc/Qwen2.5-7B-Instruct-CARE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sheryc/Qwen2.5-7B-Instruct-CARE

SGLang

How to use sheryc/Qwen2.5-7B-Instruct-CARE 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 "sheryc/Qwen2.5-7B-Instruct-CARE" \
    --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": "sheryc/Qwen2.5-7B-Instruct-CARE",
		"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 "sheryc/Qwen2.5-7B-Instruct-CARE" \
        --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": "sheryc/Qwen2.5-7B-Instruct-CARE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sheryc/Qwen2.5-7B-Instruct-CARE with Docker Model Runner:
```
docker model run hf.co/sheryc/Qwen2.5-7B-Instruct-CARE
```

Qwen2.5-7B-Instruct-CARE

Model Card for Qwen2.5-7B-Instruct-CARE

Model Description

CARE-Qwen2.5-7B-Instruct is a 7.61B parameter instruction-tuned language model based on Qwen2.5-7B-Instruct, enhanced with native retrieval-augmented reasoning capabilities through the CARE (Context-Aware Retrieval-Enhanced reasoning) framework. This model has been specifically trained to improve context fidelity and reduce hallucinations by teaching the model to explicitly integrate in-context evidence within its reasoning process.

Key Features:

Native retrieval-augmented reasoning: Dynamically identifies and incorporates relevant evidence from input context
Improved context fidelity: Significantly better adherence to provided context, especially when it contradicts parametric knowledge
Enhanced multi-hop reasoning: Superior performance on complex reasoning tasks requiring evidence integration
Structured reasoning output: Generates reasoning chains with explicit evidence citations using <think> and <retrieval> tags

Model Details

Model Type: Causal Language Model (Enhanced with Retrieval-Augmented Reasoning)
Base Model: Qwen2.5-7B-Instruct
Parameters: 7.61B total, 6.53B non-embedding
Architecture: Transformer with RoPE, SwiGLU, RMSNorm, and Attention QKV bias
Context Length: 131,072 tokens (full), 8,192 tokens (generation)
Training Framework: Two-phase training (SFT + Reinforcement Learning with GRPO)

Training Process

The model was trained using a novel two-phase approach:

Phase 1 - Supervised Fine-Tuning (SFT):

Dataset: 7,739 instances from HotpotQA with retrieval-augmented reasoning chains
Purpose: Establish evidence integration patterns and reasoning format
Training: 3 epochs with LoRA (r=8, α=16), AdamW optimizer

Phase 2 - Reinforcement Learning:

Method: Group Relative Policy Optimization (GRPO)
Curriculum Learning: Gradual transition from DROP (easy) to MS MARCO (hard)
Rewards: Accuracy + Format + Retrieval consistency
Training: 350 steps with multi-aspect reward optimization

System Prompt

The model uses an enhanced system prompt that enables structured reasoning with evidence retrieval:

You are Qwen, created by Alibaba Cloud. You are a helpful assistant. You FIRST think about the reasoning process as an internal monologue and then provide the final answer. The reasoning process MUST BE enclosed within <think> </think> tags. WITHIN the thinking process, make reference to the relevant texts in the prompt that provide critical information to move the reasoning process forward. The referenced texts MUST BE enclosed within <retrieval> </retrieval> tags, and MUST BE placed within the reasoning process only. The final answer MUST BE put at the end of the response after "Answer:".

Note: This system prompt is automatically applied when using the default chat template.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "sheryc/Qwen2.5-7B-Instruct-CARE"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Example usage
context = """John went to the movies with his mom last week. They watched the latest superhero movie, which was quite popular. The ticket price was $15. According to the local cinema's website, ticket prices range from $10 to $12 for regular screenings and from $13 to $16 for special releases."""

question = "Was the ticket price John's mom paid for the movie reasonable?"

messages = [
    {"role": "user", "content": f"{question}\n\nContext:{context}"}
]

tokenized_chat = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt"
)

generated_ids = model.generate(tokenized_chat.to(model.device), max_new_tokens=512)
output_text = tokenizer.decode(outputs[0])

Expected Output Format:

<think>
The context states John watched the latest superhero movie. <retrieval>The ticket price was $15.</retrieval> The context provides price ranges: <retrieval>ticket prices range from $10 to $12 for regular screenings and from $13 to $16 for special releases.</retrieval> Since this was a popular latest superhero movie, it likely qualifies as a special release. Therefore, the $15 price falls within the $13-$16 range for special releases.
</think>

Answer: Yes, the ticket price was reasonable.

Training Data

SFT Phase: HotpotQA with labeled supporting facts (7,739 instances)
RL Phase:
- DROP dataset (77,409 training instances) - Easy curriculum phase
- MS MARCO - Hard curriculum phase
Evaluation: LongBench, CofCA, and other QA benchmarks

License

Please refer to the original Qwen2.5 license terms.

Citation

@inproceedings{wang2025care,
  title={Improving Context Fidelity via Native Retrieval-Augmented Reasoning},
  author={Wang, Suyuchen and Wang, Jinlin and Wang, Xinyu and Li, Shiqi and Tang, Xiangru and Hong, Sirui and Chang, Xiao-Wen and Wu, Chenglin and Liu, Bang},
  booktitle={Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year={2025}
}

@misc{qwen2.5,
    title = {Qwen2.5: A Party of Foundation Models},
    url = {https://qwenlm.github.io/blog/qwen2.5/},
    author = {Qwen Team},
    month = {September},
    year = {2024}
}