Instructions to use OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2 with Transformers:

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

pipe = pipeline("text-generation", model="OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2")
model = AutoModelForMultimodalLM.from_pretrained("OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2")
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 OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2

SGLang

How to use OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2 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 "OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2" \
    --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": "OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2",
		"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 "OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2" \
        --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": "OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2 with Docker Model Runner:
```
docker model run hf.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct

This is by far the most completely uncensored Llama 3 8b instruct model. It will literally never refuse anything. So as a reminder, with great power comes great responsibility.

In terms of reasoning and intelligence, this model is probably worse than the OG model because of the decensoring. However, if you have issues with refusals then this will be superior just because it will not refuse.

OpenLLM Benchmark:

Training:

4096 sequence length, while the base model is 8192 sequence length. From testing it still performs the same 8192 context just fine.
Training duration is around 3 days on an RTX 4090, using 4-bit loading and Qlora 64-rank 128-alpha resulting in ~2% trainable weights.
Added DPO fine tuning aside from a more curated dataset for this v0.2 model.

Instruct format:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Quants:

FP16: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2

GGUF: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2-GGUF

Downloads last month: 9

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2

Quantizations

3 models

OwenArli
/

ArliAI-Llama-3-8B-Cumulus-v0.2

Model tree for OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2

Spaces using OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.2 9