Instructions to use chenhaodev/patient-edu-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use chenhaodev/patient-edu-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/patient-edu-qa:Q8_0
# Run inference directly in the terminal:
llama cli -hf chenhaodev/patient-edu-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/patient-edu-qa:Q8_0
# Run inference directly in the terminal:
llama cli -hf chenhaodev/patient-edu-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/patient-edu-qa:Q8_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf chenhaodev/patient-edu-qa:Q8_0

Use Docker

docker model run hf.co/chenhaodev/patient-edu-qa:Q8_0

Llama new
LM Studio
Jan

vLLM

How to use chenhaodev/patient-edu-qa with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chenhaodev/patient-edu-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/patient-edu-qa",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/chenhaodev/patient-edu-qa:Q8_0

Ollama
How to use chenhaodev/patient-edu-qa with Ollama:
```
ollama run hf.co/chenhaodev/patient-edu-qa:Q8_0
```
Unsloth Desktop

How to use chenhaodev/patient-edu-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/patient-edu-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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "chenhaodev/patient-edu-qa:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use chenhaodev/patient-edu-qa with Docker Model Runner:
```
docker model run hf.co/chenhaodev/patient-edu-qa:Q8_0
```

Lemonade

How to use chenhaodev/patient-edu-qa with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull chenhaodev/patient-edu-qa:Q8_0

Run and chat with the model

lemonade run user.patient-edu-qa-Q8_0

List all available models

lemonade list

Hermes Agent

How to use chenhaodev/patient-edu-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/patient-edu-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://127.0.0.1:8080/v1
hermes config set model.default chenhaodev/patient-edu-qa:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use chenhaodev/patient-edu-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/patient-edu-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://127.0.0.1:8080/v1 \
  --custom-model-id "chenhaodev/patient-edu-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"

patient-edu-qa / scripts /merge_router_data.py

chenhaodev

Initial upload: patient-edu-qa harness (code, data, LoRA, router GGUF)

784ea73 verified 27 days ago

Raw History Blame Contribute Delete

1.73 kB

#!/usr/bin/env python3
"""Merge curated + augmented router data into a balanced train/val SFT dataset."""
import json
import os
import random

ROOT = "/workspace/TASK18/data/router"
CUR = os.path.join(ROOT, "router_train.jsonl")        # 12093 grounded single-intent
AUG = os.path.join(ROOT, "router_augmented.jsonl")    # alert + compound

random.seed(42)


def load(p):
    return [json.loads(l) for l in open(p, encoding="utf-8")]


cur = load(CUR)
aug = load(AUG)

# split augmented: hold out some alert & compound for val
random.shuffle(aug)
n_aug_val = max(30, int(len(aug) * 0.2))
aug_val, aug_train = aug[:n_aug_val], aug[n_aug_val:]

# from curated, keep a representative grounded sample for train, plus a small val set
random.shuffle(cur)
val_cur = cur[:300]
pool_cur = cur[300:]

# limit grounded pool in train to balance (alert ~200, keep grounded ~ few thousand)
GROUND_TRAIN_CAP = 3000
train_cur = pool_cur[:GROUND_TRAIN_CAP]

train = aug_train + train_cur
val = aug_val + val_cur

# dedup train by utterance
seen = set()
train_dedup = []
for r in train:
    u = r["utterance"]
    if u in seen:
        continue
    seen.add(u)
    train_dedup.append(r)

from collections import Counter


def mode_of(r):
    return json.loads(r["messages"][1]["content"]).get("mode", "grounded")


print("train:", len(train_dedup), Counter(mode_of(r) for r in train_dedup))
print("val  :", len(val), Counter(mode_of(r) for r in val))

for name, recs in (("router_sft_train.jsonl", train_dedup), ("router_sft_val.jsonl", val)):
    with open(os.path.join(ROOT, name), "w", encoding="utf-8") as f:
        for r in recs:
            f.write(json.dumps(r, ensure_ascii=False) + "\n")
    print("saved ->", os.path.join(ROOT, name))

	#!/usr/bin/env python3
	"""Merge curated + augmented router data into a balanced train/val SFT dataset."""
	import json
	import os
	import random

	ROOT = "/workspace/TASK18/data/router"
	CUR = os.path.join(ROOT, "router_train.jsonl") # 12093 grounded single-intent
	AUG = os.path.join(ROOT, "router_augmented.jsonl") # alert + compound

	random.seed(42)


	def load(p):
	return [json.loads(l) for l in open(p, encoding="utf-8")]


	cur = load(CUR)
	aug = load(AUG)

	# split augmented: hold out some alert & compound for val
	random.shuffle(aug)
	n_aug_val = max(30, int(len(aug) * 0.2))
	aug_val, aug_train = aug[:n_aug_val], aug[n_aug_val:]

	# from curated, keep a representative grounded sample for train, plus a small val set
	random.shuffle(cur)
	val_cur = cur[:300]
	pool_cur = cur[300:]

	# limit grounded pool in train to balance (alert ~200, keep grounded ~ few thousand)
	GROUND_TRAIN_CAP = 3000
	train_cur = pool_cur[:GROUND_TRAIN_CAP]

	train = aug_train + train_cur
	val = aug_val + val_cur

	# dedup train by utterance
	seen = set()
	train_dedup = []
	for r in train:
	u = r["utterance"]
	if u in seen:
	continue
	seen.add(u)
	train_dedup.append(r)

	from collections import Counter


	def mode_of(r):
	return json.loads(r["messages"][1]["content"]).get("mode", "grounded")


	print("train:", len(train_dedup), Counter(mode_of(r) for r in train_dedup))
	print("val :", len(val), Counter(mode_of(r) for r in val))

	for name, recs in (("router_sft_train.jsonl", train_dedup), ("router_sft_val.jsonl", val)):
	with open(os.path.join(ROOT, name), "w", encoding="utf-8") as f:
	for r in recs:
	f.write(json.dumps(r, ensure_ascii=False) + "\n")
	print("saved ->", os.path.join(ROOT, name))