Instructions to use Syed-Hasan-8503/Llama-3-8b-instruct-SimPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Syed-Hasan-8503/Llama-3-8b-instruct-SimPO with Transformers:

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

pipe = pipeline("text-generation", model="Syed-Hasan-8503/Llama-3-8b-instruct-SimPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Syed-Hasan-8503/Llama-3-8b-instruct-SimPO")
model = AutoModelForCausalLM.from_pretrained("Syed-Hasan-8503/Llama-3-8b-instruct-SimPO")
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 Syed-Hasan-8503/Llama-3-8b-instruct-SimPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Syed-Hasan-8503/Llama-3-8b-instruct-SimPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Syed-Hasan-8503/Llama-3-8b-instruct-SimPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Syed-Hasan-8503/Llama-3-8b-instruct-SimPO

SGLang

How to use Syed-Hasan-8503/Llama-3-8b-instruct-SimPO 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 "Syed-Hasan-8503/Llama-3-8b-instruct-SimPO" \
    --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": "Syed-Hasan-8503/Llama-3-8b-instruct-SimPO",
		"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 "Syed-Hasan-8503/Llama-3-8b-instruct-SimPO" \
        --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": "Syed-Hasan-8503/Llama-3-8b-instruct-SimPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Syed-Hasan-8503/Llama-3-8b-instruct-SimPO with Docker Model Runner:
```
docker model run hf.co/Syed-Hasan-8503/Llama-3-8b-instruct-SimPO
```

outputs

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the Syed-Hasan-8503/orpo-40k-train-test dataset. It achieves the following results on the evaluation set:

Loss: 0.9751
Rewards/chosen: -3.4539
Rewards/rejected: -5.6604
Rewards/accuracies: 0.7613
Rewards/margins: 2.2065
Logps/rejected: -2.2642
Logps/chosen: -1.3816
Logits/rejected: -1.3683
Logits/chosen: -1.2117

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: 2
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 3
gradient_accumulation_steps: 2
total_train_batch_size: 12
total_eval_batch_size: 12
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
1.645	0.0140	50	1.2563	-2.7945	-3.7325	0.7027	0.9380	-1.4930	-1.1178	-1.3468	-1.1841
0.8722	0.0280	100	1.0619	-3.0769	-4.7343	0.7320	1.6574	-1.8937	-1.2308	-1.3817	-1.2196
1.0404	0.0419	150	0.9883	-3.4545	-5.6160	0.7545	2.1615	-2.2464	-1.3818	-1.3639	-1.2082
1.4672	0.0559	200	0.9751	-3.4539	-5.6604	0.7613	2.2065	-2.2642	-1.3816	-1.3683	-1.2117