Upload folder using huggingface_hub

README.md

@@ -0,0 +1,77 @@
+---
+license: other
+license_name: nvidia-oneway-noncommercial
+license_link: https://huggingface.co/nvidia/audio-flamingo-next-think-hf
+base_model: nvidia/audio-flamingo-next-think-hf
+library_name: peft
+pipeline_tag: audio-text-to-text
+tags:
+- audio
+- audio-reasoning
+- reinforcement-learning
+- grpo
+- self-supervised-learning
+- lora
+---
+
+# Audio-R1 — Audio Flamingo Next Think (LoRA)
+
+LoRA adapter for [nvidia/audio-flamingo-next-think-hf](https://huggingface.co/nvidia/audio-flamingo-next-think-hf) trained with **Audio-R1**, an RL post-training framework that uses audio self-supervised tasks as a source of verifiable rewards.
+
+- **Paper:** [Audio-R1: Audio Reasoning through Reinforcement Learning on Self-Supervised Tasks](https://arxiv.org/abs/2610.34609)
+- **Project page:** https://ijihoon98.github.io/Audio-R1/
+
+## Training
+
+| | |
+|---|---|
+| Method | GRPO (ms-swift), 8 rollouts per prompt, temperature 0.8, β = 0.04 |
+| Tasks | Identity Detection + Region Inpainting (joint, 2 tasks; Temporal Ordering is left out for this backbone, see the paper's appendix) |
+| Rewards | think-format guard + answer-letter correctness |
+| Audio sources | LibriSpeech, VoxCeleb2, MELD, CoVoST2 (en/zh), multi-speaker mixtures, AF-Think |
+| LoRA | r = 8, α = 32, dropout 0.05, language model + audio projector; audio encoder frozen |
+| Optimization | lr 5e-6, 1 epoch, 1,906 steps, effective batch 32 prompts |
+
+## Usage
+
+```python
+import librosa, torch
+from peft import PeftModel
+from transformers import AutoProcessor, MusicFlamingoForConditionalGeneration
+
+base = "nvidia/audio-flamingo-next-think-hf"
+processor = AutoProcessor.from_pretrained(base)
+model = MusicFlamingoForConditionalGeneration.from_pretrained(base, dtype=torch.float32, device_map="auto")
+model = PeftModel.from_pretrained(model, "NearAndDear98/Audio-R1-AF-Next-Think").eval()
+
+SYSTEM = (
+    "Your response MUST contain two parts in this exact order: "
+    "1. Your reasoning enclosed within <think> </think> tags. "
+    "2. The final answer — a single letter for the correct option — enclosed "
+    "within <answer> </answer> tags."
+)
+question = "<sound>\nQuestion ...\n(A) ...\n(B) ...\n(C) ...\n(D) ..."   # one <sound> per audio
+prompt = processor.apply_chat_template(
+    [{"role": "system", "content": SYSTEM}, {"role": "user", "content": question}],
+    tokenize=False, add_generation_prompt=True,
+)
+audios = [librosa.load("example.wav", sr=16000, mono=True)[0]]
+inputs = processor(text=[prompt], audio=audios, return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=512, do_sample=False)
+print(processor.batch_decode(out[:, inputs["input_ids"].shape[-1]:], skip_special_tokens=True)[0])
+```
+
+## License
+
+The base model is released under the NVIDIA OneWay Noncommercial License; this adapter inherits those terms and is for **non-commercial research use only**.
+
+## Citation
+
+```bibtex
+@article{jeong2026audior1,
+  title   = {Audio-R1: Audio Reasoning through Reinforcement Learning on Self-Supervised Tasks},
+  author  = {Jeong, Jihoon and Ravanelli, Mirco and Wang, Zhepei and Subakan, Cem},
+  journal = {arXiv preprint arXiv:2610.34609},
+  year    = {2026}
+}
+```

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "nvidia/audio-flamingo-next-think-hf",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(model\\.language_model(?=\\.).*\\.(q_proj|gate_proj|up_proj|down_proj|v_proj|k_proj|o_proj)|model\\.multi_modal_projector(?=\\.).*\\.(linear_1|linear_2))$",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf735e89535cce3dd41f0c71b03254205c332aacf4e3ae4f374dac2d0f3707a
+size 40621152