Instructions to use mlabonne/NeuralMarcoro14-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlabonne/NeuralMarcoro14-7B with Transformers:

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

pipe = pipeline("text-generation", model="mlabonne/NeuralMarcoro14-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlabonne/NeuralMarcoro14-7B")
model = AutoModelForCausalLM.from_pretrained("mlabonne/NeuralMarcoro14-7B", 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 mlabonne/NeuralMarcoro14-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlabonne/NeuralMarcoro14-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlabonne/NeuralMarcoro14-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlabonne/NeuralMarcoro14-7B

SGLang

How to use mlabonne/NeuralMarcoro14-7B 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 "mlabonne/NeuralMarcoro14-7B" \
    --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": "mlabonne/NeuralMarcoro14-7B",
		"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 "mlabonne/NeuralMarcoro14-7B" \
        --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": "mlabonne/NeuralMarcoro14-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mlabonne/NeuralMarcoro14-7B with Docker Model Runner:
```
docker model run hf.co/mlabonne/NeuralMarcoro14-7B
```

NeuralMarcoro14-7B / README.md

mlabonne

Update README.md

be69189 over 2 years ago

2.72 kB

license: apache-2.0
tags:
  - mlabonne/Marcoro14-7B-slerp
  - dpo
  - rlhf
datasets:
  - mlabonne/chatml_dpo_pairs

NeuralMarcoro14-7B

This is a DPO fine-tune version of mlabonne/Marcoro14-7B-slerp. It improves the performance of the model on Nous benchmark suite (waiting for the results on the Open LLM Benchmark).

🏆 Evaluation

Model	AGIEval	GPT4ALL	TruthfulQA	Bigbench	Average
Marcoro14-7B-slerp	44.66	76.24	64.15	45.64	57.67
NeuralMarcoro14-7B	44.59	76.17	65.94	46.9	58.4
Change	-0.07	-0.07	+1.79	+1.26	+0.73

🧩 Training hyperparameters

LoRA:

r=16
lora_alpha=16
lora_dropout=0.05
bias="none"
task_type="CAUSAL_LM"
target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']

Training arguments:

per_device_train_batch_size=4
gradient_accumulation_steps=4
gradient_checkpointing=True
learning_rate=5e-5
lr_scheduler_type="cosine"
max_steps=200
optim="paged_adamw_32bit"
warmup_steps=100

DPOTrainer:

beta=0.1
max_prompt_length=1024
max_length=1536

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/NeuralMarcoro14-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Output:

Large Language Models (LLMs) are advanced artificial intelligence systems designed to process and generate human language. They are trained on vast amounts of text data to understand context, grammar, vocabulary, and various linguistic patterns. These models can perform tasks such as translation, summarization, text completion, question answering, and more, mimicking human-like language capabilities. Examples of well-known LLMs include GPT-3 by OpenAI and BERT by Google. Their size, measured in billions of parameters, allows them to achieve impressive results in natural language understanding and generation.