Text Generation
Transformers
GGUF
English
phi
knowledge-system
reasoning
expert-verification
multi-domain
zero-hallucination
spatial-memory
knowledge-tiles
phi-4
microsoft
knowledge-tiles-iath
conversational
Eval Results (legacy)
Instructions to use kofdai/nullai-knowledge-system with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kofdai/nullai-knowledge-system with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kofdai/nullai-knowledge-system") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("kofdai/nullai-knowledge-system") model = AutoModelForCausalLM.from_pretrained("kofdai/nullai-knowledge-system") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - llama-cpp-python
How to use kofdai/nullai-knowledge-system with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="kofdai/nullai-knowledge-system", filename="phi-4-q4_K_M.gguf", )
llm.create_chat_completion( messages = [ { "role": "user", "content": "What is the capital of France?" } ] ) - Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use kofdai/nullai-knowledge-system with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf kofdai/nullai-knowledge-system:Q4_K_M # Run inference directly in the terminal: llama-cli -hf kofdai/nullai-knowledge-system:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf kofdai/nullai-knowledge-system:Q4_K_M # Run inference directly in the terminal: llama-cli -hf kofdai/nullai-knowledge-system:Q4_K_M
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 kofdai/nullai-knowledge-system:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf kofdai/nullai-knowledge-system:Q4_K_M
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 kofdai/nullai-knowledge-system:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf kofdai/nullai-knowledge-system:Q4_K_M
Use Docker
docker model run hf.co/kofdai/nullai-knowledge-system:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use kofdai/nullai-knowledge-system with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kofdai/nullai-knowledge-system" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kofdai/nullai-knowledge-system", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/kofdai/nullai-knowledge-system:Q4_K_M
- SGLang
How to use kofdai/nullai-knowledge-system with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "kofdai/nullai-knowledge-system" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kofdai/nullai-knowledge-system", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "kofdai/nullai-knowledge-system" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kofdai/nullai-knowledge-system", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Ollama
How to use kofdai/nullai-knowledge-system with Ollama:
ollama run hf.co/kofdai/nullai-knowledge-system:Q4_K_M
- Unsloth Studio new
How to use kofdai/nullai-knowledge-system with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for kofdai/nullai-knowledge-system to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for kofdai/nullai-knowledge-system to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for kofdai/nullai-knowledge-system to start chatting
- Docker Model Runner
How to use kofdai/nullai-knowledge-system with Docker Model Runner:
docker model run hf.co/kofdai/nullai-knowledge-system:Q4_K_M
- Lemonade
How to use kofdai/nullai-knowledge-system with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull kofdai/nullai-knowledge-system:Q4_K_M
Run and chat with the model
lemonade run user.nullai-knowledge-system-Q4_K_M
List all available models
lemonade list
Upload coordinate_mapper.py with huggingface_hub
Browse files- coordinate_mapper.py +103 -0
coordinate_mapper.py
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import math
|
| 2 |
+
from typing import Dict, Any, List
|
| 3 |
+
|
| 4 |
+
# 既存のモジュールをインポート
|
| 5 |
+
# calculate_granularity は粒度を計算するもので、ドメインに依存しないためそのまま利用
|
| 6 |
+
from certainty_calculation_formula import calculate_granularity
|
| 7 |
+
|
| 8 |
+
def assign_verification_score(concepts: list, sources: list) -> float:
|
| 9 |
+
"""検証スコアを割り当てるダミー関数"""
|
| 10 |
+
score = 50.0
|
| 11 |
+
if sources:
|
| 12 |
+
score += len(sources) * 5.0
|
| 13 |
+
return score
|
| 14 |
+
|
| 15 |
+
class CoordinateMapper:
|
| 16 |
+
"""
|
| 17 |
+
LLMの思考プロセス(推論ステップ)を、動的に読み込まれたドメインスキーマに
|
| 18 |
+
基づいてドメイン固有の空間座標に変換する汎用マッパー。
|
| 19 |
+
"""
|
| 20 |
+
def __init__(self, domain_schema: Dict[str, Any]):
|
| 21 |
+
"""
|
| 22 |
+
特定のドメインスキーマを元にマッパーを初期化します。
|
| 23 |
+
|
| 24 |
+
Args:
|
| 25 |
+
domain_schema (Dict[str, Any]): 対象ドメインのスキーマ。
|
| 26 |
+
"""
|
| 27 |
+
if not domain_schema:
|
| 28 |
+
raise ValueError("ドメインスキーマが提供されていません。")
|
| 29 |
+
self.schema = domain_schema
|
| 30 |
+
self.keyword_map = self.schema.get("keyword_map", {})
|
| 31 |
+
|
| 32 |
+
def map_reasoning_to_domain_space(self, reasoning_steps: List[Dict]) -> List[Dict]:
|
| 33 |
+
"""
|
| 34 |
+
抽出された推論ステップを、当マッパーに設定されたドメインの空間座標に変換します。
|
| 35 |
+
|
| 36 |
+
Args:
|
| 37 |
+
reasoning_steps (List[Dict]): reasoning_chain_extractor.pyから得られる推論ステップのリスト。
|
| 38 |
+
|
| 39 |
+
Returns:
|
| 40 |
+
List[Dict]: 座標情報が付与された辞書のリスト。
|
| 41 |
+
"""
|
| 42 |
+
coordinates = []
|
| 43 |
+
full_text = " ".join(step["text"] for step in reasoning_steps)
|
| 44 |
+
|
| 45 |
+
# 全体のテキストから主要な座標を推定(デフォルト値として使用)
|
| 46 |
+
default_coord = [50, 50, 50]
|
| 47 |
+
axis_map = {'x': 0, 'y': 1, 'z': 2}
|
| 48 |
+
for axis_name, axis_index in axis_map.items():
|
| 49 |
+
axis_keywords = [kw for kw in self.keyword_map if self.keyword_map[kw]['axis'] == axis_name and kw in full_text]
|
| 50 |
+
if axis_keywords:
|
| 51 |
+
default_coord[axis_index] = self.keyword_map[axis_keywords[0]]['coord']
|
| 52 |
+
|
| 53 |
+
for step in reasoning_steps:
|
| 54 |
+
coord = list(default_coord)
|
| 55 |
+
# ステップ内のキーワードで座標を上書き
|
| 56 |
+
step_keywords = [kw for kw in self.keyword_map if kw in step["text"]]
|
| 57 |
+
for kw in step_keywords:
|
| 58 |
+
axis_name = self.keyword_map[kw]['axis']
|
| 59 |
+
axis_index = axis_map[axis_name]
|
| 60 |
+
coord[axis_index] = self.keyword_map[kw]['coord']
|
| 61 |
+
|
| 62 |
+
# メタ軸の計算
|
| 63 |
+
c = int(step["confidence"] * 100)
|
| 64 |
+
word_count = len(step["text"].split())
|
| 65 |
+
g = calculate_granularity(word_count)
|
| 66 |
+
v = assign_verification_score(step["concepts"], [])
|
| 67 |
+
|
| 68 |
+
coordinates.append({
|
| 69 |
+
"step_sequence": step["sequence"],
|
| 70 |
+
"reasoning_text": step["text"],
|
| 71 |
+
"coordinate": {
|
| 72 |
+
"medical_space": tuple(coord), # スキーマ名に合わせて変更が必要だが、ここでは固定
|
| 73 |
+
"meta_space": (c, g, v)
|
| 74 |
+
},
|
| 75 |
+
"concept_tags": step["concepts"],
|
| 76 |
+
"confidence": step["confidence"]
|
| 77 |
+
})
|
| 78 |
+
|
| 79 |
+
return coordinates
|
| 80 |
+
|
| 81 |
+
# --- 使用例 ---
|
| 82 |
+
if __name__ == "__main__":
|
| 83 |
+
from domain_manager import DomainManager
|
| 84 |
+
from reasoning_chain_extractor import extract_reasoning_chain
|
| 85 |
+
|
| 86 |
+
# 1. ドメインマネージャを初期化
|
| 87 |
+
domain_manager = DomainManager()
|
| 88 |
+
|
| 89 |
+
# 2. ダミーの推論ステップを用意
|
| 90 |
+
dummy_reasoning_chain = [
|
| 91 |
+
{'sequence': 0, 'text': 'まず、民法における契約の定義から始めます。', 'confidence': 0.9, 'concepts': ['民法', '契約']},
|
| 92 |
+
{'sequence': 1, 'text': '次に、具体的な判例を元に解釈を深めます。', 'confidence': 0.8, 'concepts': ['判例', '解釈']}
|
| 93 |
+
]
|
| 94 |
+
|
| 95 |
+
# 3. 法学ドメイン用のマッパーを生成して実行
|
| 96 |
+
print("--- Case: Legal Domain ---")
|
| 97 |
+
legal_schema = domain_manager.get_schema("legal")
|
| 98 |
+
legal_mapper = CoordinateMapper(legal_schema)
|
| 99 |
+
|
| 100 |
+
legal_coordinates = legal_mapper.map_reasoning_to_domain_space(dummy_reasoning_chain)
|
| 101 |
+
|
| 102 |
+
import json
|
| 103 |
+
print(json.dumps(legal_coordinates, indent=2, ensure_ascii=False))
|