Text Generation
Safetensors
GGUF
Chinese
diet-nutrition
patient-education
qa
rag
qwen3
lora
retrieval-augmented-generation
health-routing
conversational
Instructions to use chenhaodev/diet-nutrition-qa 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 chenhaodev/diet-nutrition-qa 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 chenhaodev/diet-nutrition-qa:Q8_0 # Run inference directly in the terminal: llama cli -hf chenhaodev/diet-nutrition-qa:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf chenhaodev/diet-nutrition-qa:Q8_0 # Run inference directly in the terminal: llama cli -hf chenhaodev/diet-nutrition-qa:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf chenhaodev/diet-nutrition-qa:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf chenhaodev/diet-nutrition-qa:Q8_0
Use Docker
docker model run hf.co/chenhaodev/diet-nutrition-qa:Q8_0
- Llama new
- LM Studio
- Jan
- vLLM
How to use chenhaodev/diet-nutrition-qa with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "chenhaodev/diet-nutrition-qa" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "chenhaodev/diet-nutrition-qa", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/chenhaodev/diet-nutrition-qa:Q8_0
- Ollama
How to use chenhaodev/diet-nutrition-qa with Ollama:
ollama run hf.co/chenhaodev/diet-nutrition-qa:Q8_0
- Unsloth Desktop
- Pi
How to use chenhaodev/diet-nutrition-qa with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf chenhaodev/diet-nutrition-qa:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "chenhaodev/diet-nutrition-qa:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use chenhaodev/diet-nutrition-qa with Docker Model Runner:
docker model run hf.co/chenhaodev/diet-nutrition-qa:Q8_0
- Lemonade
How to use chenhaodev/diet-nutrition-qa with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull chenhaodev/diet-nutrition-qa:Q8_0
Run and chat with the model
lemonade run user.diet-nutrition-qa-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use chenhaodev/diet-nutrition-qa with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf chenhaodev/diet-nutrition-qa:Q8_0
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default chenhaodev/diet-nutrition-qa:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use chenhaodev/diet-nutrition-qa with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf chenhaodev/diet-nutrition-qa:Q8_0
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "chenhaodev/diet-nutrition-qa:Q8_0" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download scripts/red_flag_rules.py from chenhaodev/diet-nutrition-qa: direct link, hf CLI and curl.
- Browser
- Download file 10.3 kB
-
https://huggingface.co/chenhaodev/diet-nutrition-qa/resolve/main/scripts/red_flag_rules.py
- Command line
-
hf download hf://chenhaodev/diet-nutrition-qa/scripts/red_flag_rules.py
-
curl -L -o red_flag_rules.py https://huggingface.co/chenhaodev/diet-nutrition-qa/resolve/main/scripts/red_flag_rules.py
10.3 kB
| #!/usr/bin/env python3 | |
| """Red-flag rule engine + scanner for the diet/nutrition patient Q&A harness. | |
| Slow up-front decision: red-flags (mode=alert) are SAFETY-CRITICAL and therefore | |
| kept deterministic (rules), never left to the small router — this mirrors TASK18's | |
| "hybrid" lesson. The rules below are tuned to the three knowledge domains: | |
| GI diseases, diabetes ditetics, osteoporosis. | |
| Returns, per utterance: | |
| red_flags[] : [{type, severity, trigger}] | |
| sub_intents[] (category + intent from rules, used as the deterministic fallback) | |
| mode : "alert" | "grounded" | |
| """ | |
| import re | |
| # ---------------------------------------------------------------------------- | |
| # A. duration / temporal flags (shared chronic/acute/progressive logic) | |
| # ---------------------------------------------------------------------------- | |
| _CN_NUM = {"一":1,"两":2,"二":2,"三":3,"四":4,"五":5,"六":6,"七":7,"八":8,"九":9,"十":10,"半":0.5,"几":3} | |
| _DUR_UNIT = r"(?:个)?(周|星期|天|日|个月|月|年)" | |
| _DUR_RE = re.compile(r"([0-9]{1,3}(?:\.[0-9])?|[一二两三四五六七八九十半几]+?)\s*" + _DUR_UNIT) | |
| def _parse_cn_num(s): | |
| if s.replace(".", "", 1).isdigit(): | |
| return float(s) | |
| if s == "半": | |
| return 0.5 | |
| total = 0 | |
| if "十" in s: | |
| a, _, b = s.partition("十") | |
| total = (_CN_NUM.get(a, 0) if a else 1) * 10 + _CN_NUM.get(b, 0) | |
| else: | |
| total = sum(_CN_NUM.get(ch, 0) for ch in s) | |
| return total | |
| def _duration_flags(text): | |
| flags = [] | |
| seen = set() | |
| for m in _DUR_RE.finditer(text): | |
| n = _parse_cn_num(m.group(1)) | |
| unit = m.group(2) | |
| ctx = text[max(0, m.start() - 14):m.start()] | |
| if re.search(r"(?:怀孕|孕|妊娠|孕周|胎)", ctx): | |
| continue | |
| if re.search(r"(?:岁|出生|生后|月龄)", ctx) and unit in ("周", "天", "个月"): | |
| continue | |
| is_chronic = False | |
| if unit in ("年",): | |
| is_chronic = True | |
| elif unit in ("个月", "月"): | |
| is_chronic = n >= 1 | |
| elif unit in ("周", "星期"): | |
| is_chronic = n >= 2 | |
| elif unit in ("天", "日"): | |
| if n >= 14: | |
| is_chronic = True | |
| elif re.search(r"(?:持续|一直|老是|总是|反复)", ctx) and n >= 7: | |
| is_chronic = True | |
| if is_chronic and "chronicity" not in seen: | |
| flags.append(({"type": "chronicity", "severity": "high"}, "duration:" + m.group(0))) | |
| seen.add("chronicity") | |
| if re.search(r"(?:突然|突发|骤然|一下子|猛地|爆裂)", text.lower()): | |
| flags.append(({"type": "acuteness", "severity": "high"}, "acute-onset")) | |
| if re.search(r"(?:越来越(?:严重|疼|痛|差)|进行性|加重|恶化|持续加重)", text): | |
| flags.append(({"type": "progression", "severity": "high"}, "worsening")) | |
| return flags | |
| # ---------------------------------------------------------------------------- | |
| # B. domain-specific dangerous-signal entities (GI / diabetes / osteoporosis) | |
| # ---------------------------------------------------------------------------- | |
| _ENTITY_RULES = [ | |
| # --- GI bleeding / red-flag GI --- | |
| (r"(?:呕血|吐血|咯血|黑便|柏油样便|柏油便|便血|大便带血|拉血)", "gi_bleed", "gi-bleeding"), | |
| (r"(?:突然|突发|剧烈|刀割样|钻心样|持续).{0,6}(?:腹痛|胃痛|上腹痛)|腹痛.{0,4}(?:剧烈|难忍|持续加重|刀割样)", "gi_acute", "acute-pper-abdomen"), | |
| (r"(?:吃什么吐什么|一直吐|不停吐|反复呕吐|吐个不停|持续呕吐|呕出)", "gi", "persistent-vomiting"), | |
| (r"(?:吞咽困难|进食(?:哽咽|梗阻|困难|不下)|咽不下|食物卡住)?进行?性(?:吞咽困难|进食梗阻)", "gi_obstruct", "dysphagia-progressive"), | |
| (r"(?:不明原因|莫名|悄悄|不知不觉).{0,6}(?:消瘦|体重(?:下降|减轻|变瘦))|进行性消瘦|明显变瘦", "gi_alarm", "unexplained-weight-loss"), | |
| (r"(?:大便变细|排便习惯(?:改变|改变持续)|长期腹胀伴(?:痛|疼))", "gi_alarm", "bowel-habit-change"), | |
| (r"(?:反复|长期|持续).{0,4}(?:便血|大便带血|黑便)|便血量(?:大|多)|大量便血", "gi_bleed", "significant-rectal-bleed"), | |
| (r"(?:发热|发烧).{0,8}(?:腹痛|腹痛)|腹痛.{0,8}(?:发热|发烧)", "gi_infect", "abdominal-pain-with-fever"), | |
| # --- diabetes emergencies --- | |
| (r"(?:低血糖|血糖(?:过低|骤降))", "dm_low", "hypoglycemia"), | |
| (r"(?:冷汗|出(?:冷汗|汗)|心慌|手抖|哆嗦|冒汗).{0,8}(?:心慌|冷汗|发冷|饥饿|头晕)", "dm_hypoglycemia", "hypoglycemia-symptoms"), | |
| (r"(?:意识(?:模糊|不清|丧失)|昏迷|晕倒|昏睡|叫不醒)", "dm_altered", "dm-altered-consciousness"), | |
| (r"(?:酮症酸中毒|烂苹果味|血糖(?:极高|很高|爆表))", "dm_dka", "dm-ketoacidosis"), | |
| (r"血糖[=为::]?\s*\d{3,}(?:\s*mg|\s*mmol)?", "dm_high", "very-high-glucose"), | |
| # --- osteoporosis --- | |
| (r"(?:跌倒|摔倒|摔伤|扭伤).{0,6}(?:骨|髋|腰|脊椎|脊柱)|骨折|骨裂", "bone", "fall-fracture"), | |
| (r"(?:剧烈|突发|难忍|持续).{0,4}(?:骨痛|骨折痛|腰背剧痛)|(?:腰背|背部).{0,4}(?:剧痛|剧烈疼痛)", "bone", "severe-bone-pain"), | |
| ] | |
| def _entity_flags(text): | |
| flags = [] | |
| for pat, cat, tag in _ENTITY_RULES: | |
| if re.search(pat, text, re.IGNORECASE): | |
| flags.append(({"type": cat, "severity": "high"}, tag)) | |
| return flags | |
| # ---------------------------------------------------------------------------- | |
| # C. population flags (affect diet advice) | |
| # ---------------------------------------------------------------------------- | |
| _POP_RULES = [ | |
| (r"(?:怀孕|孕妇|妊娠|孕产妇|哺乳|月子|产妇)", "pregnancy"), | |
| (r"(?:婴?儿|新生(?:儿|宝宝)|宝宝|幼童)", "infant_child"), | |
| (r"(?:老年人|老人|高龄)", "elderly"), | |
| (r"(?:透析|肾病|肾功能(?:不全|衰竭)|化疗|放疗|术后|手术后)", "comorbid"), | |
| ] | |
| def _pop_flags(text): | |
| flags = [] | |
| for pat, tag in _POP_RULES: | |
| if re.search(pat, text, re.IGNORECASE): | |
| flags.append(({"type": "population", "severity": "medium"}, tag)) | |
| return flags | |
| # ---------------------------------------------------------------------------- | |
| # D. deterministic category + intent (fallback; must equal RAG index dir names) | |
| # ---------------------------------------------------------------------------- | |
| _CATEGORY_KEYS = { | |
| "esophagus-cancer": [r"食管癌|食管|食道癌|吞咽困难|噎"], | |
| "gastritis": [r"胃炎|胃病|胃黏膜|浅表性胃|萎缩性胃|幽门螺杆菌|胃痛|胃胀|反酸"], | |
| "peptic-ulcer": [r"溃疡|消化性溃疡|胃溃疡|十二指肠溃疡|便血.*溃疡"], | |
| "stomach-cancer": [r"胃癌|胃镜.*癌|胃部肿瘤"], | |
| "diarrhea": [r"腹泻|拉肚子|拉稀|便溏|急性肠炎|肠道菌群"], | |
| "gi-bleeding": [r"消化道出血|上消化道出血|下消化道出血|呕血|黑便|柏油便|便血"], | |
| "colorectal-cancer": [r"大肠癌|结肠癌|直肠癌|肠癌|肠息肉|结肠镜|肠镜"], | |
| "constipation": [r"便秘|排便困难|通便|大便干|排便不畅"], | |
| "ibs": [r"肠易激|肠易激综合征|功能性胃肠"], | |
| "ibd": [r"炎性肠病|溃疡性结肠炎|克罗恩|肠道炎症"], | |
| "diabetes": [r"糖尿|血糖|胰岛素|糖耐量|糖化|低血糖"], | |
| "osteoporosis": [r"骨质疏松|骨量|补钙|钙剂|骨密度|骨折|软骨|股骨|髋部|骨骼|维.?d|维生素d"], | |
| } | |
| def _category(text): | |
| lo = text.lower() | |
| for cat, pats in _CATEGORY_KEYS.items(): | |
| if any(re.search(p, lo) for p in pats): | |
| return cat | |
| return None | |
| _INTENT_RULES = [ | |
| ("what-eat", r"(?:能吃什么|吃什么|可以吃|能吃|适合吃|推荐吃|多吃|宜吃|吃什么好)"), | |
| ("what-avoid", r"(?:不能吃|不要吃|忌口|忌食|禁食|避免吃|少吃|不宜吃|禁忌|远离哪些|不能碰|不能喝)"), | |
| ("diet-advice", r"(?:饮食|膳食|调理|怎么吃|怎么喝|食疗|饮食上|饮食注意|怎么补)"), | |
| ("nutrient", r"(?:补钙|钙剂|钙片|维生素|营养(?:素)?|蛋白质|膳食纤维|矿物质|元素|铁|锌|磷|镁|脂肪|盐|糖分)"), | |
| ("meal-plan", r"(?:食谱|食谱|一日|三餐|早餐|晚餐|午餐|搭配|餐次|加餐|一周|怎么安排)"), | |
| ("lifestyle", r"(?:运动|锻炼|晒太阳|阳光|作息|睡眠|生活习惯|戒烟|戒酒|饮酒|抽烟)"), | |
| ("definition", r"(?:是什么|什么是|怎么回事|了解|认识|了解下)"), | |
| ("when-seek-care", r"(?:就医|看医生|医院|急诊|什么时候.*(?:去|看)|需不需|要不要.*医生)"), | |
| ] | |
| def _intent(text, cat): | |
| if not cat: | |
| return "other" | |
| lo = text.lower() | |
| for it, pat in _INTENT_RULES: | |
| if re.search(pat, lo): | |
| return it | |
| return "other" | |
| # ---------------------------------------------------------------------------- | |
| def scan(text): | |
| red = [] | |
| for data, tag in _duration_flags(text): | |
| data["trigger"] = tag | |
| red.append(data) | |
| for data, tag in _entity_flags(text): | |
| data["trigger"] = tag | |
| red.append(data) | |
| for data, tag in _pop_flags(text): | |
| data["trigger"] = tag | |
| red.append(data) | |
| has_alert = any(f["type"] not in ("population",) for f in red) | |
| mode = "alert" if has_alert else "grounded" | |
| cat = _category(text) | |
| intent = _intent(text, cat) if cat else "other" | |
| subs = [{ | |
| "intent": intent, "entity": "", "category": cat, | |
| "level": "basics", "tmpl": intent, "risk": "high" if red else "low", | |
| }] if cat else [] | |
| return red, subs, mode | |
| if __name__ == "__main__": | |
| tests = [ | |
| "我最近两天大便发黑,还呕血了,怎么办", | |
| "糖尿病病人可以吃肉吗,肉类吃多少合适", | |
| "老年人要补钙,每天吃多少维生素D合适", | |
| "我胃病反复发作好几个月了,吃什么能调理", | |
| "今天不小心摔了一跤,髋部一直很疼,会不会骨折", | |
| "怀孕的孕妇怎么补钙比较好", | |
| "我低血糖发作了,出冷汗心慌手抖", | |
| ] | |
| for t in tests: | |
| red, subs, mode = scan(t) | |
| print(f"\nQ: {t}\n mode={mode} red={[f['trigger'] for f in red]} cat={subs[0]['category'] if subs else None} intent={subs[0]['intent'] if subs else None}") | |