Instructions to use francescofiamingo1/FF_3.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use francescofiamingo1/FF_3.1 with Transformers:

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

pipe = pipeline("text-generation", model="francescofiamingo1/FF_3.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("francescofiamingo1/FF_3.1")
model = AutoModelForCausalLM.from_pretrained("francescofiamingo1/FF_3.1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use francescofiamingo1/FF_3.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "francescofiamingo1/FF_3.1"
# 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_3.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/francescofiamingo1/FF_3.1

SGLang

How to use francescofiamingo1/FF_3.1 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_3.1" \
    --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_3.1",
		"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_3.1" \
        --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_3.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use francescofiamingo1/FF_3.1 with Docker Model Runner:
```
docker model run hf.co/francescofiamingo1/FF_3.1
```

FF_3.1

FF_3.1 is a 2.02B parameter GPT-2 decoder-only language model trained from scratch with a multi-stage pipeline combining supervised fine-tuning, preference optimization, knowledge distillation, and instruction tuning.

Model Details


Architecture	GPT-2 decoder-only
Parameters	2.02B
Hidden size (d)	2048
Attention heads (h)	16
FFN size (ff)	8192
Layers (L)	38
Context length	2048
Tokenizer	GPT-2 BPE (vocab size: 50,257)
Precision	bfloat16

Training Pipeline

FF_3.1 was trained through a 5-stage pipeline:

Pretraining — 90B tokens on a large English corpus
SFT — 760K + 100K examples (OpenHermes-2.5 / NuminaMath / Eurus)
DPO — 38,863 preference pairs
Distillation v3 — 47K examples targeting MMLU + GSM8K + ARC benchmarks
LoRA v4b — 10K examples for instruction following refinement

Evaluation

Benchmark	Score
MMLU (5-shot)	27.94% (+3.94 pp vs FF_3 baseline of 24%)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("francescofiamingo1/FF_3.1", torch_dtype="bfloat16")
tokenizer = AutoTokenizer.from_pretrained("francescofiamingo1/FF_3.1")

input_text = "Explain photosynthesis in simple terms."
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Known Limitations

Math reasoning is still weak — the model struggles with multi-step arithmetic and word problems
Instruction count following is imprecise — the model may not reliably follow constraints like "list exactly 5 items"

What's Next

FF_3.2 will focus on:

DPO with UltraFeedback dataset for improved preference alignment
Improved math dataset for stronger quantitative reasoning

License

Apache 2.0

Downloads last month: 3

Safetensors

Model size

2B params

Tensor type

BF16

Evaluation results

5-shot accuracy on MMLU
self-reported

27.940