Instructions to use RAY2L/Llama-3-Instruct-8B-SimPOW-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RAY2L/Llama-3-Instruct-8B-SimPOW-1 with Transformers:

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

pipe = pipeline("text-generation", model="RAY2L/Llama-3-Instruct-8B-SimPOW-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RAY2L/Llama-3-Instruct-8B-SimPOW-1")
model = AutoModelForCausalLM.from_pretrained("RAY2L/Llama-3-Instruct-8B-SimPOW-1")
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 RAY2L/Llama-3-Instruct-8B-SimPOW-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RAY2L/Llama-3-Instruct-8B-SimPOW-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RAY2L/Llama-3-Instruct-8B-SimPOW-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RAY2L/Llama-3-Instruct-8B-SimPOW-1

SGLang

How to use RAY2L/Llama-3-Instruct-8B-SimPOW-1 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 "RAY2L/Llama-3-Instruct-8B-SimPOW-1" \
    --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": "RAY2L/Llama-3-Instruct-8B-SimPOW-1",
		"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 "RAY2L/Llama-3-Instruct-8B-SimPOW-1" \
        --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": "RAY2L/Llama-3-Instruct-8B-SimPOW-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RAY2L/Llama-3-Instruct-8B-SimPOW-1 with Docker Model Runner:
```
docker model run hf.co/RAY2L/Llama-3-Instruct-8B-SimPOW-1
```

llama-3-8b-instruct-simpo

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the princeton-nlp/llama3-ultrafeedback dataset. It achieves the following results on the evaluation set:

Loss: 0.7528
Original Losses: 2.0491
Weight: 0.3713
Abs Diff: 3.1759
Rewards/chosen: -45.3959
Rewards/rejected: -50.3664
Rewards/accuracies: 0.6976
Rewards/margins: 4.9705
Logps/rejected: -20.1465
Logps/chosen: -18.1584
Logits/rejected: 1.8309
Logits/chosen: 1.7177
All Logps 1: -7614.6904
All Logps 1 Values: -7614.6909
All Logps 2: 414.8609
All Logps 2 Values: 414.8609

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: 8
gradient_accumulation_steps: 8
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: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Original Losses	Weight	Abs Diff	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen	All Logps 1	All Logps 1 Values	All Logps 2	All Logps 2 Values
0.7506	0.8549	400	0.7528	2.0491	0.3713	3.1759	-45.3959	-50.3664	0.6976	4.9705	-20.1465	-18.1584	1.8309	1.7177	-7614.6904	-7614.6909	414.8609	414.8609

Framework versions

Transformers 4.41.2
Pytorch 2.2.2+cu121
Datasets 2.20.0
Tokenizers 0.19.1

Downloads last month: 1

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for RAY2L/Llama-3-Instruct-8B-SimPOW-1

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Finetuned

(1118)

this model

RAY2L
/

Llama-3-Instruct-8B-SimPOW-1

llama-3-8b-instruct-simpo

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for RAY2L/Llama-3-Instruct-8B-SimPOW-1

Dataset used to train RAY2L/Llama-3-Instruct-8B-SimPOW-1