upwitu/qwen3-4b-sft-all-lora

flowchart TD
    subgraph Papers["1. Architectural Foundations (IJCAI 2026 Winners)"]
        P1["10CARS<br/>(L1-L3 Pre-Flight Gate & Read-Before-Write)"]
        P2["FreudeDrive<br/>(4-Step CoT & Parameter Provenance)"]
        P3["Proxima Ultra<br/>(Programmatic CodeAct & Policy-as-Code)"]
    end

    subgraph DataGen["2. Synthesis & Sanitization Engine"]
        GEN["sft_generator (Async Multi-Worker Engine)"]
        SAN["scripts/sanitize_dataset.py<br/>(Tool ID Binding & Schema Repair)"]
        D1["carbench_sft_multirole_json.jsonl (1,324 samples)"]
        D2["carbench_sft_codeact_python.jsonl (1,443 samples)"]
        GEN --> SAN
        SAN --> D1
        SAN --> D2
    end

    subgraph Training["3. Supervised Fine-Tuning (SFT)"]
        BASE["Base Model: Qwen3-4B-Instruct-2507"]
        LORA["LoRA Adapter (r=16, alpha=32, 142MB)<br/>Targets: q, k, v, o, gate, up, down_proj<br/>Loss: 0.7222 | Epochs: 2.0 | 148 steps"]
        MERGE["Merged 16-Bit Weights: upwitu/qwen3-4b-sft-all"]
        BASE --> LORA --> MERGE
    end

    Papers --> DataGen
    D1 --> LORA
    D2 --> LORA

sequenceDiagram
    autonumber
    actor Driver as Driver / Evaluator
    participant Host as Python Inference Host (Transformers + PEFT)
    participant Model as Qwen3-4B + LoRA Adapter
    participant Vehicle as In-Cabin Vehicle Actuators (58 Tools)

    Driver->>Host: Voice command: "Turn on fog lights."
    Host->>Model: Apply Chat Template & Invariant Directives
    Note over Model: Generates 4-Step CoT reasoning:<br/>[Context Audit] -> [Policy Check] -> [Tool Selection] -> [Plan]
    Model-->>Host: Function Call: get_weather()
    Host->>Vehicle: get_weather()
    Vehicle-->>Host: {"weather": "foggy", "visibility": "low"}
    Host->>Model: Supply weather observation
    Model-->>Host: Function Call: set_fog_lights(on=true)
    Host->>Vehicle: set_fog_lights(on=true)
    Vehicle-->>Host: {"status": "success", "fog_lights": true}
    Host->>Model: Supply execution confirmation
    Model-->>Host: Voice response: "Fog lights are now activated."
    Host-->>Driver: Natural Speech Output

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

base_model_id = "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit"
adapter_id = "upwitu/qwen3-4b-sft-all-lora"

tokenizer = AutoTokenizer.from_pretrained(base_model_id)
base_model = AutoModelForCausalLM.from_pretrained(
    base_model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)
model = PeftModel.from_pretrained(base_model, adapter_id)

messages = [
    {"role": "system", "content": "You are a professional in-cabin autonomous vehicle AI assistant."},
    {"role": "user", "content": "Turn on fog lights."}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.2)
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)

flowchart TD
    subgraph NenTang["1. Nền Tảng Lý Thuyết (3 Đội Vô Địch IJCAI 2026)"]
        P1["10CARS<br/>(Cổng Tiền Bay L3 & Đọc Trước Khi Ghi)"]
        P2["FreudeDrive<br/>(CoT 4 Bước & Xác Thực Nguồn Gốc ID)"]
        P3["Proxima Ultra<br/>(Programmatic CodeAct & Policy-as-Code)"]
    end

    subgraph SinhDuLieu["2. Động Cơ Sinh & Chuẩn Hóa Dữ Liệu"]
        GEN["sft_generator (Engine Bất Đồng Bộ Đa Luồng)"]
        SAN["scripts/sanitize_dataset.py<br/>(Gắn ID Tool & Chuẩn Hóa Cú Pháp)"]
        D1["carbench_sft_multirole_json.jsonl (1,324 mẫu)"]
        D2["carbench_sft_codeact_python.jsonl (1,443 mẫu)"]
        GEN --> SAN
        SAN --> D1
        SAN --> D2
    end

    subgraph HuanLuyen["3. Tinh Chỉnh LoRA Chuyên Biệt"]
        BASE["Mô Hình Gốc: Qwen3-4B-Instruct-2507"]
        LORA["Adapter LoRA (r=16, alpha=32, 142MB)<br/>Module: q, k, v, o, gate, up, down_proj<br/>Loss: 0.7222 | Epochs: 2.0 | 148 steps"]
        MERGE["Trọng Số Hợp Nhất 16-Bit: upwitu/qwen3-4b-sft-all"]
        BASE --> LORA --> MERGE
    end

    NenTang --> SinhDuLieu
    D1 --> LORA
    D2 --> LORA

sequenceDiagram
    autonumber
    actor TaiXe as Tài Xế / Giám Sát Viên
    participant Host as Ứng Dụng Host (Transformers + PEFT)
    participant MoHinh as Mô Hình Qwen3-4B + LoRA Adapter
    participant Xe as Hệ Thống Chấp Hành Trên Xe (58 Công Cụ)

    TaiXe->>Host: Khẩu lệnh: "Bật đèn sương mù."
    Host->>MoHinh: Nạp Chat Template & Ràng Buộc Tiền Bay
    Note over MoHinh: Sinh chuỗi suy luận CoT 4 bước:<br/>[Context Audit] -> [Policy Check] -> [Tool Selection] -> [Plan]
    MoHinh-->>Host: Function Call: get_weather()
    Host->>Xe: get_weather()
    Xe-->>Host: {"weather": "foggy", "visibility": "low"}
    Host->>MoHinh: Nạp quan sát thời tiết từ cảm biến xe
    MoHinh-->>Host: Function Call: set_fog_lights(on=true)
    Host->>Xe: set_fog_lights(on=true)
    Xe-->>Host: {"status": "success", "fog_lights": true}
    Host->>MoHinh: Xác nhận thực thi thành công
    MoHinh-->>Host: Phản hồi giọng nói: "Đèn sương mù đã được bật."
    Host-->>TaiXe: Câu thoại tự nhiên