Instructions to use siqi00/Mistral-7B-DFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use siqi00/Mistral-7B-DFT with Transformers:

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

pipe = pipeline("text-generation", model="siqi00/Mistral-7B-DFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("siqi00/Mistral-7B-DFT")
model = AutoModelForCausalLM.from_pretrained("siqi00/Mistral-7B-DFT")
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 siqi00/Mistral-7B-DFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "siqi00/Mistral-7B-DFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "siqi00/Mistral-7B-DFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/siqi00/Mistral-7B-DFT

SGLang

How to use siqi00/Mistral-7B-DFT 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 "siqi00/Mistral-7B-DFT" \
    --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": "siqi00/Mistral-7B-DFT",
		"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 "siqi00/Mistral-7B-DFT" \
        --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": "siqi00/Mistral-7B-DFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use siqi00/Mistral-7B-DFT with Docker Model Runner:
```
docker model run hf.co/siqi00/Mistral-7B-DFT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Mistral-7B-DFT

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the siqi00/mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320 dataset. It was finetuned as part of the paper Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data

The code is available at https://github.com/PenGuln/DFT.

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-06
train_batch_size: 4
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2

Framework versions

Transformers 4.45.2
Pytorch 2.1.2+cu121
Datasets 3.0.1
Tokenizers 0.20.1

Usage Example

The model can be used for text generation tasks. A basic example using the transformers library is shown below:

from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
import torch

model_id = "siqi00/Mistral-7B-DFT"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)

prompt = "What is the capital of France?"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
generation_config = GenerationConfig(max_new_tokens=20, temperature=0.7)
outputs = model.generate(inputs["input_ids"], generation_config=generation_config)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)

Remember to install the necessary libraries (pip install transformers) and adjust parameters like temperature and max_new_tokens to fine-tune generation.

Citation

@misc{guo2025discriminativefinetuninggenerativelarge,
      title={Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data}, 
      author={Siqi Guo and Ilgee Hong and Vicente Balmaseda and Tuo Zhao and Tianbao Yang},
      year={2025},
      eprint={2502.18679},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2502.18679}, 
}

Downloads last month: 16

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for siqi00/Mistral-7B-DFT

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(928)

this model

Quantizations

1 model

Dataset used to train siqi00/Mistral-7B-DFT

Paper for siqi00/Mistral-7B-DFT

Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data

Paper • 2502.18679 • Published Feb 25, 2025 • 2