Instructions to use feeltheAGI/maverick-llama3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use feeltheAGI/maverick-llama3-8B with Transformers:

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

pipe = pipeline("text-generation", model="feeltheAGI/maverick-llama3-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("feeltheAGI/maverick-llama3-8B")
model = AutoModelForCausalLM.from_pretrained("feeltheAGI/maverick-llama3-8B")
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

vLLM

How to use feeltheAGI/maverick-llama3-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "feeltheAGI/maverick-llama3-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "feeltheAGI/maverick-llama3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/feeltheAGI/maverick-llama3-8B

SGLang

How to use feeltheAGI/maverick-llama3-8B 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 "feeltheAGI/maverick-llama3-8B" \
    --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": "feeltheAGI/maverick-llama3-8B",
		"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 "feeltheAGI/maverick-llama3-8B" \
        --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": "feeltheAGI/maverick-llama3-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use feeltheAGI/maverick-llama3-8B with Docker Model Runner:
```
docker model run hf.co/feeltheAGI/maverick-llama3-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Maverick Llama 3 8b 🏴‍☠️

model is using ChatML prompt template format.

example:

<|im_start|>system
You are Maverick, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

🏆 Evaluation

eq-bench

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
eq_bench	2.1	none	0	eqbench	56.8710	±	2.8946
		none	0	percent_parseable	99.4152	±	0.5848

winogrande

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
winogrande	1	none	0	acc	0.7372	±	0.0124

gsm8k

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
gsm8k	3	strict-match	5	exact_match	0.5694	±	0.0136
		flexible-extract	5	exact_match	0.5701	±	0.0136

mathqa

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
mathqa	1	none	0	acc	0.3930	±	0.0089
		none	0	acc_norm	0.3869	±	0.0089

This model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT

Downloads last month: 12

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for feeltheAGI/maverick-llama3-8B

Quantizations

3 models

feeltheAGI
/

maverick-llama3-8B