Instructions to use fenguhao/llama-8b-dpo-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fenguhao/llama-8b-dpo-full with Transformers:

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

pipe = pipeline("text-generation", model="fenguhao/llama-8b-dpo-full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fenguhao/llama-8b-dpo-full")
model = AutoModelForCausalLM.from_pretrained("fenguhao/llama-8b-dpo-full", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fenguhao/llama-8b-dpo-full with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/fenguhao/llama-8b-dpo-full

SGLang

How to use fenguhao/llama-8b-dpo-full 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 "fenguhao/llama-8b-dpo-full" \
    --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": "fenguhao/llama-8b-dpo-full",
		"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 "fenguhao/llama-8b-dpo-full" \
        --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": "fenguhao/llama-8b-dpo-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fenguhao/llama-8b-dpo-full with Docker Model Runner:
```
docker model run hf.co/fenguhao/llama-8b-dpo-full
```

llama-8b-dpo-full / all_results.json

fenguhao

Model save

b002b79 verified about 2 years ago

Raw History Blame Contribute Delete

740 Bytes

	{
	"epoch": 1.0,
	"eval_logits/chosen": -1.4751973152160645,
	"eval_logits/rejected": -1.4288278818130493,
	"eval_logps/chosen": -2603.783203125,
	"eval_logps/rejected": -2200.0751953125,
	"eval_loss": 0.6315724849700928,
	"eval_rewards/accuracies": 0.6600000262260437,
	"eval_rewards/chosen": 0.6899210810661316,
	"eval_rewards/margins": 0.3855075538158417,
	"eval_rewards/rejected": 0.30441343784332275,
	"eval_runtime": 298.7044,
	"eval_samples": 2000,
	"eval_samples_per_second": 6.696,
	"eval_steps_per_second": 0.418,
	"train_loss": 0.6480738864519209,
	"train_runtime": 26013.0665,
	"train_samples": 61135,
	"train_samples_per_second": 2.35,
	"train_steps_per_second": 0.073
	}