README.md

metadata

license: apache-2.0
language:
  - en
  - it
base_model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
library_name: transformers
pipeline_tag: text-generation
tags:
  - nemotron_h
  - sync2
  - fractal-rl
  - cognitive-behaviors
  - self-improving
  - thesia
  - alignment
  - lora
  - peft
  - custom_code
  - endpoints-ready
inference:
  parameters:
    temperature: 0.7
    top_p: 0.9
    max_new_tokens: 512
    do_sample: true
widget:
  - text: |
      <|system|>You are sync2, a reasoner trained with Fractal RL.
      <|user|>Spiega in 3 punti il principio di Ollivier-Ricci.
      <|assistant|>
    example_title: Reasoning · IT
  - text: |
      <|system|>You are sync2.
      <|user|>Write a Python function for Ricci curvature on a graph.
      <|assistant|>
    example_title: Code · EN
extra_gated_prompt: >-
  Accept the Apache-2.0 license and the NVIDIA Nemotron-3 base license. The
  model embeds Lorenzo Bernardini's Fractal-RL / THESIA research; cite
  arxiv:2503.01307 for cognitive-behaviors methodology.
extra_gated_fields:
  Affiliation: text
  Country: country
  Intended use: text

Lorenzob/synch-2

Base model: nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 (120B MoE · 12B active) Variant: adapter-only (LoRA) · Final checkpoint: sync2_apogeo_si_iter1

Ready for HuggingFace Dedicated Inference Endpoints, HF Inference API, Together AI, Modal, vLLM/TGI compatible runtimes.

Quickstart · Dedicated Endpoint

from huggingface_hub import InferenceClient
client = InferenceClient("Lorenzob/synch-2", token="<HF_TOKEN>")
out = client.text_generation(
    "<|user|>Compute the Ollivier-Ricci curvature of K_5.<|assistant|>",
    max_new_tokens=512, temperature=0.7,
)
print(out)

Quickstart · Local (PEFT)

import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("Lorenzob/synch-2",
                                    trust_remote_code=True)
base = AutoModelForCausalLM.from_pretrained(
    "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16", torch_dtype=torch.bfloat16,
    device_map="auto", trust_remote_code=True,
)
model = PeftModel.from_pretrained(base, "Lorenzob/synch-2")

Suggested Hardware

AWS · 8x H100 80GB (o equivalente A100 80GB x4) — bfloat16 adapter + base = ~245 GB VRAM.

Training Pipeline

1. SFT — 9-dataset supervised fine-tuning (KIMI-K2.5, Opus-4.6-Reasoning, coding-200k, tulu-3-math, multilingual, Nettoov, MLEM, tool-reasoning).
2. EML-RLHF — symbolic regression reward (EML trees).
3. Fractal RL — GRPO con 8-component reward (coherence + fractal + Ollivier-Ricci curvature + EML + math + reasoning + length + DPP).
4. v11 APOGEO — alignment SFT (300 step) + self-improving reasoner (2 iter × 80 prompt × top-30%). Best reward +0.200.

Attribution

• Cognitive behaviors: Gandhi et al. 2025 (arXiv:2503.01307)
• Self-improving reasoner: karpathy/nanochat
• Fractal RL · LCTR · THESIA: Lorenzo Bernardini publications.

License

Apache-2.0 (this adapter) · NVIDIA Nemotron-3 license (base weights).