ModelPublicadoExterno

Angelcare Cosmos Reason2 8B

nvidia-open-model-license

Fuentehuggingface.co/Chloepv/Angelcare-Cosmos-Reason2-8B/tree/30f3bf60eb571e2a0372fa49c52e089e514d6b29

TipoOtherModelo basenvidia/Cosmos-Reason2-8BVersiónAdapter modelCcalidad

Fuente del modelo

Tipo: Other
Tamaño del archivo: 83,3 MB–16,3 GB
Modelo base: nvidia/Cosmos-Reason2-8B
Versión: vAdapter model
Actualizado: 20 oct 2026
Fuente: Hugging Face

Descripción de la fuente

AngelCare — Cosmos Reason2 8B (Fine-Tuned)

Fine-tuned nvidia/Cosmos-Reason2-8B for 8-class elderly safety video classification.

Available Models

Branch	Method	Accuracy	Description
`main`	QLoRA (4-bit NF4, r=16)	85.0%	Best model — recommended for deployment
`lora`	LoRA (fp16, r=16)	83.3%	Alternative fine-tune for comparison

Both are full merged models (adapter baked into base weights). Load directly — no need for base model or adapters.

Raw LoRA/QLoRA adapters are also available under the qlora-adapter and lora-adapter branches.

Usage

from transformers import AutoModelForCausalLM, AutoProcessor
import torch

# Load QLoRA model (best, main branch)
model = AutoModelForCausalLM.from_pretrained(
    "Chloepv/Angelcare-Cosmos-Reason2-8B",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
processor = AutoProcessor.from_pretrained("Chloepv/Angelcare-Cosmos-Reason2-8B")

# Load LoRA model (alternative)
# model = AutoModelForCausalLM.from_pretrained("Chloepv/Angelcare-Cosmos-Reason2-8B", revision="lora", ...)

Task

Given a short video clip (~5-10s) of an elderly person, classify their activity into one of 8 safety categories:

ID	Label	Risk Level
0	Fall Detected	CRITICAL
1	Prolonged Immobility	CRITICAL
2	Unsteady Movement	MEDIUM
3	Distress Posture	HIGH
4	Normal Walking	SAFE
5	Normal Sitting	SAFE
6	Normal Daily Activity	SAFE
7	Resting or Sleeping	SAFE

Output Format

The model outputs structured JSON:

{
  "prediction_class_id": 0,
  "prediction_label": "Fall Detected",
  "risk_level": "CRITICAL",
  "video_description": "The person falls from standing position onto the floor.",
  "risk_assessment": {
    "is_at_risk": true,
    "recommended_action": "Call emergency services immediately"
  }
}

Results

Overall

Metric	Base Model	QLoRA	LoRA
Accuracy	26.7%	85.0%	83.3%
JSON Compliance	65%	100%	100%
Inference Time	6.4s	1.9s	1.9s

Per-Class Accuracy (QLoRA)

Class	Accuracy
Fall (n=11)	90.9%
Unsteady (n=11)	72.7%
Distress (n=11)	100%
Sitting (n=11)	81.8%
Daily (n=10)	100%
Resting (n=3)	100%

Training Details

Dataset: 277 train / 60 test samples (LLaVA format, source-stratified split)
Sources: Harvard Dataverse, GMDC-SA24, NTU RGB+D 120, DIY annotated, personal clips, Cosmos Transfer 2.5 synthetic
Hardware: 1x NVIDIA H100 80GB (Nebius)
QLoRA config: r=16, alpha=32, dropout=0.05, lr=2e-4, 10 epochs, effective batch=8
LoRA config: r=16, alpha=32, dropout=0.05, lr=1e-4, 10 epochs, effective batch=8
Framework: TRL SFTTrainer + PEFT

Limitations

Classes with few training samples (Immobility, Walking) have 0% test accuracy due to insufficient data
Trained primarily on indoor surveillance-style videos; may not generalize to outdoor or unusual camera angles
Small dataset (277 samples) — more data would likely improve performance significantly

Citation

@misc{angelcare2026,
  title={AngelCare: Fine-tuning Cosmos Reason2 8B for Elderly Safety Video Classification},
  author={Chloe PV},
  year={2026},
  url={https://huggingface.co/Chloepv/Angelcare-Cosmos-Reason2-8B}
}

Fuentes

1 fuente

Hugging FacePrincipalVersión 30f3bf60eb571e2a0372fa49c52e089e514d6b29

huggingface.co/Chloepv/Angelcare-Cosmos-Reason2-8B/tree/30f3bf60eb571e2a0372fa49c52e089e514d6b29

Verificado 6 ago

Artefactos del modelo

4 artefactos

adapter_model.safetensors

safetensors · 83,3 MB · SHA-256 24e2c26b402d…9aa7 · Hugging Face

Descargar

checkpoint-34/adapter_model.safetensors

safetensors · 83,3 MB · SHA-256 89de422bdc16…73bb · Hugging Face

Descargar

checkpoint-51/adapter_model.safetensors

safetensors · 83,3 MB · SHA-256 24e2c26b402d…9aa7 · Hugging Face

Descargar

model.safetensors

safetensors · 16,3 GB · SHA-256 16b7e658721b…a833 · Hugging Face

Descargar

Extractos de fuentes

2 extractos

Readme6 agohuggingface.co/Chloepv/Angelcare-Cosmos-Reason2-8B

--- license: other license_name: nvidia-open-model-license base_model: nvidia/Cosmos-Reason2-8B tags: - video-classification - elderly-care - fall-detection - safety - cosmos - qwen3vl - qlora - lora - fine-tuned datasets: - custom pipeline_tag: video-classification --- # AngelCare — Cosmos Reason2 8B (Fine-Tuned) Fine-tuned [nvidia/Cosmos-Reason2-8B](https://huggingface.co/nvidia/Cosmos-Reason2-8B) for **8-class elderly safety video classification**. ## Available Models | Branch | Method | Accuracy | Description | |--------|--------|----------|-------------| | **`main`** | **QLoRA** (4-bit NF4, r=16) | **85.0%** | Best model — recommended for deployment | | `lora` | LoRA (fp16, r=16) | 83.3% | Alternative fine-tune for comparison | Both are **full merged models** (adapter baked into base weights). Load directly — no need for base model or adapters. Raw LoRA/QLoRA adapters are also available under the `qlora-adapter` and `lora-adapter` branches. ## Usage ```python from transformers import AutoModelForCausalLM, AutoProcessor import torch # Load QLoRA model (best, main branch) model = AutoModelForCausalLM.from_pretrained( "Chloepv/Angelcare-Cosmos-Reason2-8B", torch_dtype=torch.bfloat16, device_map="auto", ) processor = AutoProcessor.from_pretrained("Chloepv/Angelcare-Cosmos-Reason2-8B") # Load LoRA model (alternative) # model = AutoModelForCausalLM.from_pretrained("Chloepv/Angelcare-Cosmos-Reason2-8B", revision="lora", ...) ``` ## Task Given a short video clip (~5-10s) of an elderly person, classify their activity into one of 8 safety categories: | ID | Label | Risk Level | |----|-------|------------| | 0 | Fall Detected | CRITICAL | | 1 | Prolonged Immobility | CRITICAL | | 2 | Unsteady Movement | MEDIUM | | 3 | Distress Posture | HIGH | | 4 | Normal Walking | SAFE | | 5 | Normal Sitting | SAFE | | 6 | Normal Daily Activity | SAFE | | 7 | Resting or Sleeping | SAFE | ## Output Format The model outputs structured JSON: ```json { "prediction_class_id": 0, "prediction_label": "Fall Detected", "risk_level": "CRITICAL", "video_description": "The person falls from standing position onto the floor.", "risk_assessment": { "is_at_risk": true, "recommended_action": "Call emergency services immediately" } } ``` ## Results ### Overall | Metric | Base Model | QLoRA | LoRA | |--------|:---:|:---:|:---:| | Accuracy | 26.7% | **85....

Note6 agohuggingface.co/Chloepv/Angelcare-Cosmos-Reason2-8B

Source context: 8 downloads · 1 likes · Pipeline video-classification · Library cosmos · Repo Chloepv/Angelcare-Cosmos-Reason2-8B