Instructions to use nora-team/qwen-1.5b-grounded-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nora-team/qwen-1.5b-grounded-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/home/elicer/simon/models/qwen2.5-1.5b")
model = PeftModel.from_pretrained(base_model, "nora-team/qwen-1.5b-grounded-lora")

Transformers

How to use nora-team/qwen-1.5b-grounded-lora with Transformers:

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

pipe = pipeline("text-generation", model="nora-team/qwen-1.5b-grounded-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nora-team/qwen-1.5b-grounded-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nora-team/qwen-1.5b-grounded-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nora-team/qwen-1.5b-grounded-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nora-team/qwen-1.5b-grounded-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nora-team/qwen-1.5b-grounded-lora

SGLang

How to use nora-team/qwen-1.5b-grounded-lora 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 "nora-team/qwen-1.5b-grounded-lora" \
    --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": "nora-team/qwen-1.5b-grounded-lora",
		"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 "nora-team/qwen-1.5b-grounded-lora" \
        --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": "nora-team/qwen-1.5b-grounded-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nora-team/qwen-1.5b-grounded-lora with Docker Model Runner:
```
docker model run hf.co/nora-team/qwen-1.5b-grounded-lora
```

Qwen 2.5-1.5B Fine-tuned for Grounded Text Generation with Citations

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B using LoRA adapters. It has been trained to generate accurate answers with proper source citations based on provided documents.

Model Details

Model Description

This model generates answers to questions by:

Reading provided source documents
Generating accurate, concise answers
Citing sources using [1], [2], [3] format
Only using information from the provided documents

Developed by: sungmineom
Model type: Causal Language Model (Fine-tuned with LoRA)
Language(s): English (primary), Korean
License: Same as base model (Qwen2.5-1.5B)
Finetuned from model: Qwen/Qwen2.5-1.5B

Training Details

Training data: combined_train.json (10,000 samples)
Validation data: combined_test.json (1,000 samples)
LoRA rank: 16
LoRA alpha: 32
Batch size: 2 (with gradient accumulation steps: 8)
Learning rate: 2e-4
Epochs: 3
Max sequence length: 2048 tokens
Quantization: 4-bit (nf4) for training efficiency

Uses

Direct Use

This model is designed for Question Answering tasks where you want:

Accurate answers based on specific documents
Proper source attribution with citations
Grounded generation (no hallucination from outside sources)

Usage Example

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

# Load base model
base_model_name = "Qwen/Qwen2.5-1.5B"
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "sungmineom/qwen-1.5b-grounded-lora")
tokenizer = AutoTokenizer.from_pretrained("sungmineom/qwen-1.5b-grounded-lora")

# Prepare input
question = "What are the benefits of exercise?"
docs = [
    {"title": "Health Benefits", "text": "Exercise improves cardiovascular health..."},
    {"title": "Mental Health", "text": "Exercise reduces anxiety and depression..."}
]

doc_text = ""
for i, doc in enumerate(docs, 1):
    doc_text += f"Document [{i}](Title: {doc['title']}): {doc['text']}\n"

prompt = f"""Instruction: Write an accurate, engaging, and concise answer for the given question using only the provided search results (some of which might be irrelevant) and cite them properly. Use an unbiased and journalistic tone. Always cite for any factual claim. When citing several search results, use [1][2][3]. Cite at least one document and at most three documents in each sentence. If multiple documents support the sentence, only cite a minimum sufficient subset of the documents.

Question: {question}

{doc_text}
Answer:"""

# Generate
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)
answer = tokenizer.decode(outputs[0], skip_special_tokens=True).split("Answer:")[-1].strip()

print(answer)

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: [More Information Needed]
Hours used: [More Information Needed]
Cloud Provider: [More Information Needed]
Compute Region: [More Information Needed]
Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

PEFT 0.17.1

Downloads last month: -

Model tree for nora-team/qwen-1.5b-grounded-lora

Base model

Qwen/Qwen2.5-1.5B

Adapter

(514)

this model

Paper for nora-team/qwen-1.5b-grounded-lora

Quantifying the Carbon Emissions of Machine Learning

Paper • 1910.09700 • Published Oct 21, 2019 • 48