Instructions to use francescofiamingo1/FF_3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use francescofiamingo1/FF_3 with Transformers:

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

pipe = pipeline("text-generation", model="francescofiamingo1/FF_3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("francescofiamingo1/FF_3")
model = AutoModelForCausalLM.from_pretrained("francescofiamingo1/FF_3")

llama-cpp-python

How to use francescofiamingo1/FF_3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="francescofiamingo1/FF_3",
	filename="ff3_q4km.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use francescofiamingo1/FF_3 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf francescofiamingo1/FF_3
# Run inference directly in the terminal:
llama cli -hf francescofiamingo1/FF_3

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf francescofiamingo1/FF_3
# Run inference directly in the terminal:
llama cli -hf francescofiamingo1/FF_3

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf francescofiamingo1/FF_3
# Run inference directly in the terminal:
./llama-cli -hf francescofiamingo1/FF_3

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf francescofiamingo1/FF_3
# Run inference directly in the terminal:
./build/bin/llama-cli -hf francescofiamingo1/FF_3

Use Docker

docker model run hf.co/francescofiamingo1/FF_3

LM Studio
Jan

vLLM

How to use francescofiamingo1/FF_3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "francescofiamingo1/FF_3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "francescofiamingo1/FF_3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/francescofiamingo1/FF_3

SGLang

How to use francescofiamingo1/FF_3 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 "francescofiamingo1/FF_3" \
    --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": "francescofiamingo1/FF_3",
		"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 "francescofiamingo1/FF_3" \
        --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": "francescofiamingo1/FF_3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use francescofiamingo1/FF_3 with Ollama:
```
ollama run hf.co/francescofiamingo1/FF_3
```

Unsloth Studio

How to use francescofiamingo1/FF_3 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for francescofiamingo1/FF_3 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for francescofiamingo1/FF_3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for francescofiamingo1/FF_3 to start chatting

Atomic Chat new
Docker Model Runner
How to use francescofiamingo1/FF_3 with Docker Model Runner:
```
docker model run hf.co/francescofiamingo1/FF_3
```

Lemonade

How to use francescofiamingo1/FF_3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull francescofiamingo1/FF_3

Run and chat with the model

lemonade run user.FF_3-{{QUANT_TAG}}

List all available models

lemonade list

FF_3 — FF-LLM 2.02B

FF_3 is a 2.02B parameter language model trained from scratch.

Model Details

Architecture: GPT-2 decoder-only (custom)
Parameters: 2,022,739,072
Vocabulary: 50,257 (GPT-2 BPE tokenizer)
Context length: 2,048 tokens
Training: From scratch on 90B tokens

Training Pipeline

Pretraining: 90B tokens (web + STEM data)
SFT: 760K examples + 100K high-quality examples
DPO: 38,863 preference pairs
Distillation: 20K examples from Qwen2.5-32B teacher

Prompt Format

### System:
You are FF-LLM, a helpful assistant.

### Instruction:
{your question here}

### Response:

Usage with Transformers

from transformers import GPT2LMHeadModel, GPT2Tokenizer

model = GPT2LMHeadModel.from_pretrained("ff-llm/FF_3")
tokenizer = GPT2Tokenizer.from_pretrained("ff-llm/FF_3")

prompt = (
    "### System:\nYou are FF-LLM, a helpful assistant.\n\n"
    "### Instruction:\nWhat is the capital of France?\n\n### Response:\n"
)
input_ids = tokenizer.encode(prompt, return_tensors="pt")
output = model.generate(
    input_ids, max_new_tokens=256, do_sample=True,
    temperature=0.7, top_p=0.9,
    eos_token_id=tokenizer.eos_token_id,
    pad_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(output[0][input_ids.shape[1]:], skip_special_tokens=True))

Usage with Ollama

ollama run ff-llm/FF_3

Limitations

Weak mathematical reasoning
May hallucinate on factual questions
English only

Training Cost

~,000 total compute cost Trained by a single researcher

License

Apache 2.0

Downloads last month: 21

Safetensors

Model size

2B params

Tensor type

BF16