Instructions to use netcat420/MFANN3bv1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use netcat420/MFANN3bv1.2 with Transformers:

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

pipe = pipeline("text-generation", model="netcat420/MFANN3bv1.2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("netcat420/MFANN3bv1.2")
model = AutoModelForCausalLM.from_pretrained("netcat420/MFANN3bv1.2", 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/MFANN3bv1.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "netcat420/MFANN3bv1.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "netcat420/MFANN3bv1.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/netcat420/MFANN3bv1.2

SGLang

How to use netcat420/MFANN3bv1.2 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 "netcat420/MFANN3bv1.2" \
    --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": "netcat420/MFANN3bv1.2",
		"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 "netcat420/MFANN3bv1.2" \
        --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": "netcat420/MFANN3bv1.2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use netcat420/MFANN3bv1.2 with Docker Model Runner:
```
docker model run hf.co/netcat420/MFANN3bv1.2
```
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 family of COT models fine-tuned on a modified Alpaca training regiment involving defining a "thought-process" in the dataset in each sample, allowing the model to generate reasoning tokens before the model generates output (yes this has been in the works MUCH longer than o1 has been out!)

this is the smaller 3b model based on phi-2

If you would like to support me and keep this project going well into the future (or even free me up from the horrors of little caesars so i can work on this more lmfao) please consider donating to my patreon!! https://www.patreon.com/c/MakhiBurroughs all members get to vote on what gets done next with MFANN, addtional perks are currently in the works!

system prompt:

Instruct: {instruction} Output:

Downloads last month: 22

Safetensors

Model size

3B params

Tensor type

F32

Model tree for netcat420/MFANN3bv1.2

Base model

netcat420/MFANN-abliterated-phi2-merge-unretrained

Finetuned

(1)

this model

Quantizations

7 models

netcat420
/

MFANN3bv1.2

Model tree for netcat420/MFANN3bv1.2

Dataset used to train netcat420/MFANN3bv1.2