Instructions to use pbevan11/Mistral-Nemo-MCAI-SFT-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pbevan11/Mistral-Nemo-MCAI-SFT-DPO with Transformers:

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

pipe = pipeline("text-generation", model="pbevan11/Mistral-Nemo-MCAI-SFT-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pbevan11/Mistral-Nemo-MCAI-SFT-DPO")
model = AutoModelForCausalLM.from_pretrained("pbevan11/Mistral-Nemo-MCAI-SFT-DPO", device_map="auto")
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 pbevan11/Mistral-Nemo-MCAI-SFT-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pbevan11/Mistral-Nemo-MCAI-SFT-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pbevan11/Mistral-Nemo-MCAI-SFT-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pbevan11/Mistral-Nemo-MCAI-SFT-DPO

SGLang

How to use pbevan11/Mistral-Nemo-MCAI-SFT-DPO 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 "pbevan11/Mistral-Nemo-MCAI-SFT-DPO" \
    --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": "pbevan11/Mistral-Nemo-MCAI-SFT-DPO",
		"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 "pbevan11/Mistral-Nemo-MCAI-SFT-DPO" \
        --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": "pbevan11/Mistral-Nemo-MCAI-SFT-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pbevan11/Mistral-Nemo-MCAI-SFT-DPO with Docker Model Runner:
```
docker model run hf.co/pbevan11/Mistral-Nemo-MCAI-SFT-DPO
```

Mistral-Nemo-MCAI-SFT-DPO / README.md

pbevan11

End of training

b490da1 verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

1.93 kB

metadata

library_name: transformers
license: apache-2.0
base_model: pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-3Epochs
tags:
  - alignment-handbook
  - trl
  - dpo
  - generated_from_trainer
  - trl
  - dpo
  - generated_from_trainer
datasets:
  - pbevan11/multilingual-constitutional-preference-pairs
  - pbevan11/ultrafeedback_binarized_multilingual
model-index:
  - name: Mistral-Nemo-Instruct-MCAI-SFT-DPO-3Epochs
    results: []

Mistral-Nemo-Instruct-MCAI-SFT-DPO-3Epochs

This model is a fine-tuned version of pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-3Epochs on the pbevan11/multilingual-constitutional-preference-pairs and the pbevan11/ultrafeedback_binarized_multilingual datasets. It achieves the following results on the evaluation set:

Loss: 0.5579
Rewards/chosen: -0.4264
Rewards/rejected: -0.9042
Rewards/accuracies: 0.7466
Rewards/margins: 0.4777
Logps/rejected: -213.7833
Logps/chosen: -192.1762
Logits/rejected: 0.5653
Logits/chosen: 0.5394

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: 5e-07
train_batch_size: 6
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 48
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Framework versions

Transformers 4.45.1
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.20.0