Instructions to use netcat420/Llama3.1-MFANN-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use netcat420/Llama3.1-MFANN-8b with Transformers:

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

pipe = pipeline("text-generation", model="netcat420/Llama3.1-MFANN-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("netcat420/Llama3.1-MFANN-8b")
model = AutoModelForCausalLM.from_pretrained("netcat420/Llama3.1-MFANN-8b", 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 netcat420/Llama3.1-MFANN-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "netcat420/Llama3.1-MFANN-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": "netcat420/Llama3.1-MFANN-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/netcat420/Llama3.1-MFANN-8b

SGLang

How to use netcat420/Llama3.1-MFANN-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 "netcat420/Llama3.1-MFANN-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": "netcat420/Llama3.1-MFANN-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 "netcat420/Llama3.1-MFANN-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": "netcat420/Llama3.1-MFANN-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use netcat420/Llama3.1-MFANN-8b with Docker Model Runner:
```
docker model run hf.co/netcat420/Llama3.1-MFANN-8b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Introducing MFANN (Makhi's fully autonomous neural network) a COT uncensored dataset experiment employing a modified Alpaca training regiment with one key difference, defining a "thought-process" section within the dataset. allowing the model to learn to produce reasoning tokens before generating the output. (yes this project was started WAY before o1 came out!) if you enjoy my work, please feel free to support me on patreon here: https://www.patreon.com/c/MakhiBurroughs any support will be appreciated! I currently work at little caesars and being forced to work 10-12 hour shifts, slowing down progress on this model, so any support i get, may free up more time for me to work on this project!

gpt4all reasoning prompt: {{- '<|im_start|>system\n' }} {% if toolList|length > 0 %}You have access to the following functions: {% for tool in toolList %} Use the function '{{tool.function}}' to: '{{tool.description}}' {% if tool.parameters|length > 0 %} parameters: {% for info in tool.parameters %} {{info.name}}: type: {{info.type}} description: {{info.description}} required: {{info.required}} {% endfor %} {% endif %}

Tool Instructions

If you CHOOSE to call this function ONLY reply with the following format: '{{tool.symbolicFormat}}' Here is an example. If the user says, '{{tool.examplePrompt}}', then you reply '{{tool.exampleCall}}' After the result you might reply with, '{{tool.exampleReply}}' {% endfor %} You MUST include both the start and end tags when you use a function.

You are a helpful AI assistant who uses the functions to break down, analyze, perform, and verify complex reasoning tasks. You SHOULD try to verify your answers using the functions where possible. {% endif %} {{- '<|im_end|>\n' }} {% for message in messages %} {{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }} {% endfor %} {% if add_generation_prompt %} {{ '<|im_start|>assistant\n' }} {% endif %}

Downloads last month: 22

Safetensors

Model size

8B params

Tensor type

F32

Model tree for netcat420/Llama3.1-MFANN-8b

Base model

netcat420/MFANN-SFT-2

Finetuned

(1)

this model

Quantizations

8 models

netcat420
/

Llama3.1-MFANN-8b

Tool Instructions

Model tree for netcat420/Llama3.1-MFANN-8b

Dataset used to train netcat420/Llama3.1-MFANN-8b