Instructions to use siqi00/Mistral-7B-DFT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use siqi00/Mistral-7B-DFT2 with Transformers:

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

pipe = pipeline("text-generation", model="siqi00/Mistral-7B-DFT2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("siqi00/Mistral-7B-DFT2")
model = AutoModelForCausalLM.from_pretrained("siqi00/Mistral-7B-DFT2")
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-DFT2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "siqi00/Mistral-7B-DFT2"
# 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-DFT2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/siqi00/Mistral-7B-DFT2

SGLang

How to use siqi00/Mistral-7B-DFT2 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-DFT2" \
    --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-DFT2",
		"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-DFT2" \
        --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-DFT2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use siqi00/Mistral-7B-DFT2 with Docker Model Runner:
```
docker model run hf.co/siqi00/Mistral-7B-DFT2
```

Improve model card: Add pipeline tag, link to paper and code

by nielsr HF Staff - opened Feb 27, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-4

Files changed (1) hide show

README.md +8 -4

README.md CHANGED Viewed

@@ -1,12 +1,13 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: mistralai/Mistral-7B-v0.1
 tags:
 - alignment-handbook
 - generated_from_trainer
-datasets:
-- siqi00/mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320
 model-index:
 - name: mistral-feedbuhcp2-dft-lr2e-6-tau0.3-u_init0-s2-e2-gamma0.90-rf
   results: []
@@ -19,6 +20,9 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the siqi00/mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320 dataset.
 ### Training hyperparameters
 The following hyperparameters were used during training:
@@ -41,4 +45,4 @@ The following hyperparameters were used during training:
 - Transformers 4.45.2
 - Pytorch 2.1.2+cu121
 - Datasets 3.0.1
-- Tokenizers 0.20.1

 ---
+base_model: mistralai/Mistral-7B-v0.1
+datasets:
+- siqi00/mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320
 library_name: transformers
 license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - alignment-handbook
 - generated_from_trainer
 model-index:
 - name: mistral-feedbuhcp2-dft-lr2e-6-tau0.3-u_init0-s2-e2-gamma0.90-rf
   results: []
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the siqi00/mistral_ultrafeedback_unhelpful_chatprompt_0.7_1.0_50_320 dataset.
+This model was trained using Discriminative Fine-tuning (DFT), as described in the paper [Discriminative Finetuning of Generative Large Language Models without Reward Models and Preference Data](https://arxiv.org/abs/2502.18679). The code is available at [PenGuln/DFT](https://github.com/PenGuln/DFT).
 ### Training hyperparameters
 The following hyperparameters were used during training:
 - Transformers 4.45.2
 - Pytorch 2.1.2+cu121
 - Datasets 3.0.1
+- Tokenizers 0.20.1