Instructions to use Weyaxi/Neural-una-cybertron-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Weyaxi/Neural-una-cybertron-7b with Transformers:

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

pipe = pipeline("text-generation", model="Weyaxi/Neural-una-cybertron-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Weyaxi/Neural-una-cybertron-7b")
model = AutoModelForCausalLM.from_pretrained("Weyaxi/Neural-una-cybertron-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Weyaxi/Neural-una-cybertron-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Weyaxi/Neural-una-cybertron-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Weyaxi/Neural-una-cybertron-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Weyaxi/Neural-una-cybertron-7b

SGLang

How to use Weyaxi/Neural-una-cybertron-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 "Weyaxi/Neural-una-cybertron-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Weyaxi/Neural-una-cybertron-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Weyaxi/Neural-una-cybertron-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Weyaxi/Neural-una-cybertron-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Weyaxi/Neural-una-cybertron-7b with Docker Model Runner:
```
docker model run hf.co/Weyaxi/Neural-una-cybertron-7b
```

Neural-una-cybertron-7b

Neural-una-cybertron-7b is an fblgit/una-cybertron-7b-v2-bf16 model that has been further fine-tuned with Direct Preference Optimization (DPO) using the Intel/orca_dpo_pairs dataset.

This model was created after examining the procedure of mlabonne/NeuralHermes-2.5-Mistral-7B model. Special thanks to @mlabonne.

Addionatal Information

This model was fine-tuned on Nvidia A100-SXM4-40GB GPU.

The total training time was 1 hour and 10 minutes.

Prompt Template(s)

ChatML

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>

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

Downloads last month: 1

Safetensors

Model size

7B params

Tensor type

BF16

Weyaxi
/

Neural-una-cybertron-7b

Neural-una-cybertron-7b

Addionatal Information

Prompt Template(s)

ChatML

Training hyperparameters

Dataset used to train Weyaxi/Neural-una-cybertron-7b