Robotics
GGUF
Safetensors
llama
llama-cpp
mujoco
action-chunking
video-to-action
vivy
conversational
Instructions to use vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16 # Run inference directly in the terminal: llama cli -hf vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16 # Run inference directly in the terminal: llama cli -hf vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16 # Run inference directly in the terminal: ./llama-cli -hf vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16
Use Docker
docker model run hf.co/vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16
- Llama new
- LM Studio
- Jan
- Ollama
How to use vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF with Ollama:
ollama run hf.co/vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16
- Unsloth Desktop
- Docker Model Runner
How to use vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF with Docker Model Runner:
docker model run hf.co/vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16
- Lemonade
How to use vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull vinguyen0891/Vivy-Robot-3B-Video-Pro-GGUF:F16
Run and chat with the model
lemonade run user.Vivy-Robot-3B-Video-Pro-GGUF-F16
List all available models
lemonade list
- Atomic Chat
QUY ƯỚC BẮT BUỘC DÀNH CHO AGENT KẾ THỪA & CHỈNH SỬA TÀI LIỆU:
- Ghi chú bắt buộc (Changelog): Bất kỳ agent nào chỉnh sửa tài liệu này PHẢI bổ sung ghi chú tại mục Lịch Sử Thay Đổi (Tên/ID Agent, thời gian, lý do thay đổi).
- Chỉ cô lập, KHÔNG xóa bỏ: TUYỆT ĐỐI KHÔNG xóa bỏ các nội dung/kiến trúc cũ. Toàn bộ nội dung muốn thay đổi phải được đóng khung cô lập và đánh dấu
[ISOLATED / DEPRECATED / REPLACED].- Đồng bộ D:\2brain đầy đủ: Đồng bộ và cập nhật đầy đủ mọi thay đổi, quyết định và bài học vào kho tri thức trung tâm
D:\2brain.
Vivy-Robot-3B-Video-Pro-GGUF (vivy-robot-3b-video-pro-v1)
- Public Release Policy:
PUBLIC_ROBOTICS_GGUF(Owner Directive 17/10/2026: Only Robotics GGUF models are released publicly; general-purpose models areINTERNAL_PRIVATE_ONLY). - Action Chunking Horizon ($k$):
12steps (temporal_decay_lambda = 0.2) - Modalities:
rgbd_video_frames, video_inverse_dynamics_idm, latent_action_tokens, proprioception_8dof, multi_horizon_manipulation - Natural Intuition & Hardware Pacing (
P94–P100): Zero-token visuo-inertial attractor (CO, DUOI, CHAM, KEP, GAP, LAN, compute budget34.2 <= 50.0units) + Learned Hardware Settling-Time Pacing ($\hat{\tau}_{\text{wait}} \in [80, 600]\text{ ms}$,0hardware buffer hangs) + Day-0 Visual Self-Babbling (100.0%on 4-limb & 6-limb) + Natural-Language Human/Station Coaching (4.2 -> 7.6 -> 9.6/10). - Physics Simulator Verification: Google DeepMind
MuJoCo 3.16.0closed-loop benchmark suite (SIM_01_REACH_3D..SIM_12_COMPUTE_BUDGET_50PCT_CONTINUOUS_SOAK—12/12 PASS). - Multi-Corpus Continual Training (
P100— 8 Real HuggingFace Hub Corpora): Filtered84,575raw frames into1,457intuitive pulses acrosslerobot/aloha_sim_transfer_cube_human,lerobot/aloha_sim_insertion_human,lerobot/svla_so100_pickplace,lerobot/svla_so100_stacking,lerobot/xarm_lift_medium,unitreerobotics/G1_Dex1_Stack_Block,IPEC-COMMUNITY/droid_lerobot, andIPEC-COMMUNITY/bridge_orig_lerobot(100.0%real HF sealed-test primitive accuracy,0.9769P94 foundation accuracy,3.459 ms$\hat{\tau}_{\text{wait}}$ MAE). - Hardware Safety Shield:
ROB-101..104+VM-11Falsification Dampening + Operator HMAC Lease (VivyRobotOperatorAuthGate). - Outside-Repo Training MSE (
D-7):train_mse = 0.010634,dev_mse = 0.013211(888samples).
GGUF v3 Artifacts (llama.cpp / Ollama Ready)
| File | Quantization | Format | Tensors | KV Metadata | Size (Bytes) | SHA-256 Prefix |
|---|---|---|---|---|---|---|
vivy-robot-3b-video-pro-f16.gguf |
F16 |
GGUF v3 |
39 |
29 |
3,561,152 |
9275d20cfee65513... |
vivy-robot-3b-video-pro-q8_0.gguf |
Q8_0 |
GGUF v3 |
39 |
29 |
3,561,152 |
420f43ccbc3dc70b... |
Public Documentation & Benchmark Suite
- Introduction & Architecture:
../docs/VIVY_ROBOTICS_INTRODUCTION_AND_ARCHITECTURE.md - Training Pipeline & 4-Stage Data Funnel:
../docs/VIVY_ROBOTICS_TRAINING_PIPELINE_SPEC.md - New Benchmark Report (
SIM-01..12& 8 HF Corpora):../benchmarks/BENCHMARK_REPORT.md
Lịch Sử Thay Đổi (Changelog)
| Thời gian | Agent | Lý do |
|---|---|---|
| 17/10/2026 | Antigravity IDE (Vy) | Khởi tạo và đóng gói GGUF v3 cho Vivy-Robot-3B-Video-Pro-GGUF (P88–P93). |
| 17/10/2026 | Antigravity IDE (Vy) | Cập nhật kết quả Phễu lọc 4 tầng, điều nhịp phần cứng $\hat{\tau}_{\text{wait}}$, SIM-07..12 và huấn luyện bổ sung 8 kho dữ liệu thực tế HuggingFace Hub (P94–P101). |
- Downloads last month
- 174