Instructions to use bhavyagoyal-lexsi/simpo_final-ckps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bhavyagoyal-lexsi/simpo_final-ckps with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("bhavyagoyal-lexsi/sfted_for_simpo")
model = PeftModel.from_pretrained(base_model, "bhavyagoyal-lexsi/simpo_final-ckps")

Transformers

How to use bhavyagoyal-lexsi/simpo_final-ckps with Transformers:

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

pipe = pipeline("text-generation", model="bhavyagoyal-lexsi/simpo_final-ckps")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bhavyagoyal-lexsi/simpo_final-ckps", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bhavyagoyal-lexsi/simpo_final-ckps with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bhavyagoyal-lexsi/simpo_final-ckps

SGLang

How to use bhavyagoyal-lexsi/simpo_final-ckps 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 "bhavyagoyal-lexsi/simpo_final-ckps" \
    --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": "bhavyagoyal-lexsi/simpo_final-ckps",
		"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 "bhavyagoyal-lexsi/simpo_final-ckps" \
        --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": "bhavyagoyal-lexsi/simpo_final-ckps",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bhavyagoyal-lexsi/simpo_final-ckps with Docker Model Runner:
```
docker model run hf.co/bhavyagoyal-lexsi/simpo_final-ckps
```

Model Card for simpo_finance

This model is a fine-tuned version of bhavyagoyal-lexsi/sfted_for_simpo. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with CPO, a method introduced in Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation.

Framework versions

PEFT 0.19.1
TRL: 1.7.1
Transformers: 5.13.1
Pytorch: 2.11.0+cu128
Datasets: 5.0.1
Tokenizers: 0.22.2

Citations

Cite CPO as:

@inproceedings{xu2024contrastive,
    title        = {{Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation}},
    author       = {Haoran Xu and Amr Sharaf and Yunmo Chen and Weiting Tan and Lingfeng Shen and Benjamin Van Durme and Kenton Murray and Young Jin Kim},
    year         = 2024,
    booktitle    = {Forty-first International Conference on Machine Learning, {ICML} 2024, Vienna, Austria, July 21-27, 2024},
    publisher    = {OpenReview.net},
    url          = {https://openreview.net/forum?id=51iwkioZpn}
}

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}

Downloads last month: 7

Model tree for bhavyagoyal-lexsi/simpo_final-ckps

Base model

bhavyagoyal-lexsi/sfted_for_simpo

Adapter

(1)

this model

Paper for bhavyagoyal-lexsi/simpo_final-ckps

Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation

Paper • 2401.08417 • Published Jan 16, 2024 • 37