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

Libraries

How to use yale-nlp/MDCure-Qwen2-7B-Instruct with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yale-nlp/MDCure-Qwen2-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("yale-nlp/MDCure-Qwen2-7B-Instruct")
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]:]))

Inference
Local Apps Settings

vLLM

How to use yale-nlp/MDCure-Qwen2-7B-Instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yale-nlp/MDCure-Qwen2-7B-Instruct

SGLang

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

Docker Model Runner
How to use yale-nlp/MDCure-Qwen2-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/yale-nlp/MDCure-Qwen2-7B-Instruct
```

Add library_name and pipeline_tag

by nielsr HF Staff - opened Apr 30, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+16

-8

Files changed (1) hide show

README.md +16 -8

README.md CHANGED Viewed

@@ -1,23 +1,23 @@
 ---
-license: apache-2.0
 datasets:
 - yale-nlp/MDCure-72k
 language:
 - en
-base_model:
-- Qwen/Qwen2-7B-Instruct
 tags:
 - multi-document
 - long-context
 - Long Context
 ---
 # MDCure-Qwen2-7B-Instruct
 [📄 Paper](https://arxiv.org/pdf/2410.23463) | [🤗 HF Collection](https://huggingface.co/collections/yale-nlp/mdcure-6724914875e87f41e5445395) | [⚙️ GitHub Repo](https://github.com/yale-nlp/MDCure)
 ## Introduction
 **MDCure** is an effective and scalable procedure for generating high-quality multi-document (MD) instruction tuning data to improve MD capabilities of LLMs. Using MDCure, we construct a suite of MD instruction datasets complementary to collections such as [FLAN](https://github.com/google-research/FLAN) and fine-tune a variety of already instruction-tuned LLMs from the FlanT5, Qwen2, and LLAMA3.1 model families, up to 70B parameters in size. We additionally introduce **MDCureRM**, an evaluator model specifically designed for the MD setting to filter and select high-quality MD instruction data in a cost-effective, RM-as-a-judge fashion. Extensive evaluations on a wide range of MD and long-context benchmarks spanning various tasks show MDCure consistently improves performance over pre-trained baselines and over corresponding base models by up to 75.5%.
@@ -41,7 +41,9 @@ We recommend using the latest version of HF Transformers, or any `transformers>=
 ## Quickstart
-Below we provide a code snippet demonstrating how to load the tokenizer and model and generate content in response to an input context concerning multiple source documents and a related question or instruction. We strongly recommend to separate the texts and/or instruction using `\n\n` or `<doc-sep>` to maintain consistency with the format of the data used during training.
 ```python
 model = AutoModelForCausalLM.from_pretrained("yale-nlp/MDCure-Qwen2-7B-Instruct", device_map='auto',torch_dtype="auto")
@@ -50,7 +52,13 @@ tokenizer = AutoTokenizer.from_pretrained("yale-nlp/MDCure-Qwen2-7B-Instruct")
 source_text_1 = ...
 source_text_2 = ...
 source_text_3 = ...
-prompt = f"{source_text_1}\n\n{source_text_2}\n\n{source_text_3}\n\nWhat happened in CHAMPAIGN regarding Lovie Smith and the 2019 defense improvements? Respond with 1-2 sentences."
 messages = [
       {"role": "system", "content": "You are an assistant with strong multi-document processing skills."},
@@ -78,7 +86,7 @@ We open-source our custom multi-document instruction scoring model, MDCureRM, as
 | **MDCure-Qwen2-1.5B-Instruct**    | [🤗 HF Repo](https://huggingface.co/yale-nlp/MDCure-Qwen2-1.5B-Instruct) | **Qwen2-1.5B-Instruct** fine-tuned with MDCure-72k  |
 | **MDCure-Qwen2-7B-Instruct**      | [🤗 HF Repo](https://huggingface.co/yale-nlp/MDCure-Qwen2-7B-Instruct) | **Qwen2-7B-Instruct** fine-tuned with MDCure-72k    |
 | **MDCure-LLAMA3.1-8B-Instruct**   | [🤗 HF Repo](https://huggingface.co/yale-nlp/MDCure-LLAMA3.1-8B-Instruct) | **LLAMA3.1-8B-Instruct** fine-tuned with MDCure-72k  |
-| **MDCure-LLAMA3.1-70B-Instruct**  | [🤗 HF Repo](https://huggingface.co/yale-nlp/MDCure-LLAMA3.1-70B-Instruct) | **LLAMA3.1-70B-Instruct** fine-tuned with MDCure-72 |
 ## Citation

 ---
+base_model:
+- Qwen/Qwen2-7B-Instruct
 datasets:
 - yale-nlp/MDCure-72k
 language:
 - en
+license: apache-2.0
 tags:
 - multi-document
 - long-context
 - Long Context
+library_name: transformers
+pipeline_tag: text-generation
 ---
 # MDCure-Qwen2-7B-Instruct
 [📄 Paper](https://arxiv.org/pdf/2410.23463) | [🤗 HF Collection](https://huggingface.co/collections/yale-nlp/mdcure-6724914875e87f41e5445395) | [⚙️ GitHub Repo](https://github.com/yale-nlp/MDCure)
 ## Introduction
 **MDCure** is an effective and scalable procedure for generating high-quality multi-document (MD) instruction tuning data to improve MD capabilities of LLMs. Using MDCure, we construct a suite of MD instruction datasets complementary to collections such as [FLAN](https://github.com/google-research/FLAN) and fine-tune a variety of already instruction-tuned LLMs from the FlanT5, Qwen2, and LLAMA3.1 model families, up to 70B parameters in size. We additionally introduce **MDCureRM**, an evaluator model specifically designed for the MD setting to filter and select high-quality MD instruction data in a cost-effective, RM-as-a-judge fashion. Extensive evaluations on a wide range of MD and long-context benchmarks spanning various tasks show MDCure consistently improves performance over pre-trained baselines and over corresponding base models by up to 75.5%.
 ## Quickstart
+Below we provide a code snippet demonstrating how to load the tokenizer and model and generate content in response to an input context concerning multiple source documents and a related question or instruction. We strongly recommend to separate the texts and/or instruction using `
+` or `<doc-sep>` to maintain consistency with the format of the data used during training.
 ```python
 model = AutoModelForCausalLM.from_pretrained("yale-nlp/MDCure-Qwen2-7B-Instruct", device_map='auto',torch_dtype="auto")
 source_text_1 = ...
 source_text_2 = ...
 source_text_3 = ...
+prompt = f"{source_text_1}
+{source_text_2}
+{source_text_3}
+What happened in CHAMPAIGN regarding Lovie Smith and the 2019 defense improvements? Respond with 1-2 sentences."
 messages = [
       {"role": "system", "content": "You are an assistant with strong multi-document processing skills."},
 | **MDCure-Qwen2-1.5B-Instruct**    | [🤗 HF Repo](https://huggingface.co/yale-nlp/MDCure-Qwen2-1.5B-Instruct) | **Qwen2-1.5B-Instruct** fine-tuned with MDCure-72k  |
 | **MDCure-Qwen2-7B-Instruct**      | [🤗 HF Repo](https://huggingface.co/yale-nlp/MDCure-Qwen2-7B-Instruct) | **Qwen2-7B-Instruct** fine-tuned with MDCure-72k    |
 | **MDCure-LLAMA3.1-8B-Instruct**   | [🤗 HF Repo](https://huggingface.co/yale-nlp/MDCure-LLAMA3.1-8B-Instruct) | **LLAMA3.1-8B-Instruct** fine-tuned with MDCure-72k  |
+| **MDCure-LLAMA3.1-70B-Instruct**  | [🤗 HF Repo](https://huggingface.co/yale-nlp/MDCure-LLAMA3.1-70B-Instruct) | **LLAMA3.1-70B-Instruct** fine-tuned with MDCure-72k |
 ## Citation