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

Libraries

How to use reasonrag/Qwen2.5-7B-Instruct-ReasonRAG with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("reasonrag/Qwen2.5-7B-Instruct-ReasonRAG")
model = AutoModelForCausalLM.from_pretrained("reasonrag/Qwen2.5-7B-Instruct-ReasonRAG")
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
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use reasonrag/Qwen2.5-7B-Instruct-ReasonRAG with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/reasonrag/Qwen2.5-7B-Instruct-ReasonRAG

SGLang

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

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

Qwen2.5-7B-Instruct-ReasonRAG / README.md

Wenlin Zhang

Upload README.md

e400b7c verified about 1 year ago

preview code

Raw

History Blame Contribute Delete

2.4 kB

metadata

library_name: transformers
license: other
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: dpo_v16
    results: []

dpo_v16

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct on the dpo_mcts_rag_v8 dataset. It achieves the following results on the evaluation set:

Loss: 0.8564
Rewards/chosen: 1.0146
Rewards/rejected: -0.5767
Rewards/accuracies: 0.6204
Rewards/margins: 1.5913
Logps/chosen: -65.8051
Logps/rejected: -74.8917
Logits/chosen: -0.5108
Logits/rejected: -0.5206

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 3
gradient_accumulation_steps: 4
total_train_batch_size: 12
total_eval_batch_size: 3
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.2
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/chosen	Logps/rejected	Logits/chosen	Logits/rejected
0.9257	0.4352	500	0.9691	1.0721	-0.2211	0.6171	1.2933	-65.6133	-73.7064	-0.5575	-0.5659
0.7847	0.8703	1000	0.8689	0.7341	-0.9130	0.6223	1.6471	-66.7400	-76.0126	-0.5218	-0.5319

Framework versions

Transformers 4.49.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0