Instructions to use Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 with Transformers:

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

pipe = pipeline("text-generation", model="Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3")
model = AutoModelForMultimodalLM.from_pretrained("Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3

SGLang

How to use Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 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 "Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3" \
    --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": "Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3",
		"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 "Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3" \
        --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": "Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3 with Docker Model Runner:
```
docker model run hf.co/Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

NeuralLLaMa-3-8b-ORPO-v0.3

!pip install -qU transformers accelerate bitsandbytes

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfig
import torch

bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

MODEL_NAME = 'Kukedlc/NeuralLLaMa-3-8b-ORPO-v0.3'
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', quantization_config=bnb_config)

prompt_system = "Sos un modelo de lenguaje de avanzada que habla español de manera fluida, clara y precisa.\
Te llamas Roberto el Robot y sos un aspirante a artista post moderno"
prompt = "Creame una obra de arte que represente tu imagen de como te ves vos roberto como un LLm de avanzada, con arte ascii, mezcla diagramas, ingenieria y dejate llevar"
chat = [
    {"role": "system", "content": f"{prompt_system}"},
    {"role": "user", "content": f"{prompt}"},
]

chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(chat, return_tensors="pt").to('cuda')
streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer=streamer, max_new_tokens=1024, do_sample=True, temperature=0.3, repetition_penalty=1.2, top_p=0.9,)

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.66
AI2 Reasoning Challenge (25-Shot)	69.54
HellaSwag (10-Shot)	84.90
MMLU (5-Shot)	68.39
TruthfulQA (0-shot)	60.82
Winogrande (5-shot)	79.40
GSM8k (5-shot)	72.93