FF_3.1/README.md

language, license, tags, library_name, pipeline_tag, model-index

language	license	tags	library_name	pipeline_tag	model-index
en it	apache-2.0	text-generation gpt2 decoder-only causal-lm distillation dpo sft lora	transformers	text-generation	name results FF_3.1 task dataset metrics type name text-generation Text Generation name type MMLU cais/mmlu type value name accuracy 27.94 5-shot accuracy

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:

1. Pretraining — 90B tokens on a large English corpus
2. SFT — 760K + 100K examples (OpenHermes-2.5 / NuminaMath / Eurus)
3. DPO — 38,863 preference pairs
4. Distillation v3 — 47K examples targeting MMLU + GSM8K + ARC benchmarks
5. 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