Instructions to use tanliboy/llama-3.2-3b-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tanliboy/llama-3.2-3b-dpo with Transformers:

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

pipe = pipeline("text-generation", model="tanliboy/llama-3.2-3b-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tanliboy/llama-3.2-3b-dpo")
model = AutoModelForCausalLM.from_pretrained("tanliboy/llama-3.2-3b-dpo")
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

vLLM

How to use tanliboy/llama-3.2-3b-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tanliboy/llama-3.2-3b-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": "tanliboy/llama-3.2-3b-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tanliboy/llama-3.2-3b-dpo

SGLang

How to use tanliboy/llama-3.2-3b-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 "tanliboy/llama-3.2-3b-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": "tanliboy/llama-3.2-3b-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 "tanliboy/llama-3.2-3b-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": "tanliboy/llama-3.2-3b-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tanliboy/llama-3.2-3b-dpo with Docker Model Runner:
```
docker model run hf.co/tanliboy/llama-3.2-3b-dpo
```

llama-3.2-3b-dpo

This model is a fine-tuned version of tanliboy/llama-3.2-3b-sft on the HuggingFaceH4/orca_dpo_pairs and the HuggingFaceH4/ultrafeedback_binarized datasets. It achieves the following results on the evaluation set:

Loss: 0.6289
Rewards/chosen: 0.7479
Rewards/rejected: -3.8379
Rewards/accuracies: 0.7405
Rewards/margins: 4.5857
Logps/rejected: -370.2327
Logps/chosen: -338.3392
Logits/rejected: 0.4475
Logits/chosen: 0.3731

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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
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: 0.03
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.5801	0.4739	100	0.6840	0.6485	-2.9389	0.6899	3.5875	-361.2435	-339.3325	0.6783	0.6103
0.537	0.9479	200	0.6514	0.2045	-4.0315	0.7278	4.2360	-372.1696	-343.7731	0.5648	0.4948
0.4787	1.4218	300	0.6387	0.4099	-3.9882	0.7215	4.3981	-371.7361	-341.7187	0.5326	0.4589
0.4559	1.8957	400	0.6332	0.7690	-3.6688	0.7342	4.4379	-368.5425	-338.1277	0.4841	0.4110
0.4028	2.3697	500	0.6289	0.7479	-3.8379	0.7405	4.5857	-370.2327	-338.3392	0.4475	0.3731
0.4029	2.8436	600	0.6284	0.8504	-3.7058	0.7437	4.5562	-368.9125	-337.3143	0.4571	0.3820

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

Downloads last month: 21

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for tanliboy/llama-3.2-3b-dpo

Base model

tanliboy/llama-3.2-3b

Finetuned

tanliboy/llama-3.2-3b-sft

Finetuned

(3)

this model

tanliboy
/

llama-3.2-3b-dpo

llama-3.2-3b-dpo

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for tanliboy/llama-3.2-3b-dpo

Datasets used to train tanliboy/llama-3.2-3b-dpo