Instructions to use obiwit/llama3.2-3b-orpo-finegrained-OLD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use obiwit/llama3.2-3b-orpo-finegrained-OLD with Transformers:

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

pipe = pipeline("text-generation", model="obiwit/llama3.2-3b-orpo-finegrained-OLD")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("obiwit/llama3.2-3b-orpo-finegrained-OLD")
model = AutoModelForCausalLM.from_pretrained("obiwit/llama3.2-3b-orpo-finegrained-OLD", 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 obiwit/llama3.2-3b-orpo-finegrained-OLD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "obiwit/llama3.2-3b-orpo-finegrained-OLD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "obiwit/llama3.2-3b-orpo-finegrained-OLD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/obiwit/llama3.2-3b-orpo-finegrained-OLD

SGLang

How to use obiwit/llama3.2-3b-orpo-finegrained-OLD 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 "obiwit/llama3.2-3b-orpo-finegrained-OLD" \
    --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": "obiwit/llama3.2-3b-orpo-finegrained-OLD",
		"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 "obiwit/llama3.2-3b-orpo-finegrained-OLD" \
        --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": "obiwit/llama3.2-3b-orpo-finegrained-OLD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use obiwit/llama3.2-3b-orpo-finegrained-OLD with Docker Model Runner:
```
docker model run hf.co/obiwit/llama3.2-3b-orpo-finegrained-OLD
```

llama3.2-3b-orpo-finegrained-OLD / eval_results.json

obiwit

End of training

452942a verified about 1 year ago

Raw

History Blame Contribute Delete

730 Bytes

	{
	"epoch": 0.9999635741084762,
	"eval_log_odds_chosen": 0.9230248332023621,
	"eval_log_odds_ratio": -0.5139190554618835,
	"eval_logits/chosen": -0.882161021232605,
	"eval_logits/rejected": -0.7823830246925354,
	"eval_logps/chosen": -0.6252197027206421,
	"eval_logps/rejected": -1.228542447090149,
	"eval_loss": 1.046362042427063,
	"eval_nll_loss": 1.0217794179916382,
	"eval_rewards/accuracies": 0.7051994800567627,
	"eval_rewards/chosen": -0.031262174248695374,
	"eval_rewards/margins": 0.03016679547727108,
	"eval_rewards/rejected": -0.06142931059002876,
	"eval_runtime": 1393.0666,
	"eval_samples": 98364,
	"eval_samples_per_second": 70.219,
	"eval_steps_per_second": 1.098
	}