Instructions to use Ssum-mer/qwen3.8-27b-growpath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ssum-mer/qwen3.8-27b-growpath with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Ssum-mer/qwen3.8-27b-growpath")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Ssum-mer/qwen3.8-27b-growpath")
model = AutoModelForMultimodalLM.from_pretrained("Ssum-mer/qwen3.8-27b-growpath", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ssum-mer/qwen3.8-27b-growpath 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 Ssum-mer/qwen3.8-27b-growpath:BF16
# Run inference directly in the terminal:
llama cli -hf Ssum-mer/qwen3.8-27b-growpath:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ssum-mer/qwen3.8-27b-growpath:BF16
# Run inference directly in the terminal:
llama cli -hf Ssum-mer/qwen3.8-27b-growpath:BF16

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 Ssum-mer/qwen3.8-27b-growpath:BF16
# Run inference directly in the terminal:
./build/bin/llama cli -hf Ssum-mer/qwen3.8-27b-growpath:BF16

Use Docker

docker model run hf.co/Ssum-mer/qwen3.8-27b-growpath:BF16

Llama new
LM Studio
Jan

vLLM

How to use Ssum-mer/qwen3.8-27b-growpath with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ssum-mer/qwen3.8-27b-growpath"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ssum-mer/qwen3.8-27b-growpath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ssum-mer/qwen3.8-27b-growpath:BF16

SGLang

How to use Ssum-mer/qwen3.8-27b-growpath 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 "Ssum-mer/qwen3.8-27b-growpath" \
    --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": "Ssum-mer/qwen3.8-27b-growpath",
		"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 "Ssum-mer/qwen3.8-27b-growpath" \
        --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": "Ssum-mer/qwen3.8-27b-growpath",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Ssum-mer/qwen3.8-27b-growpath with Ollama:
```
ollama run hf.co/Ssum-mer/qwen3.8-27b-growpath:BF16
```
Unsloth Desktop

How to use Ssum-mer/qwen3.8-27b-growpath with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ssum-mer/qwen3.8-27b-growpath:BF16

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": "Ssum-mer/qwen3.8-27b-growpath:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Ssum-mer/qwen3.8-27b-growpath with Docker Model Runner:
```
docker model run hf.co/Ssum-mer/qwen3.8-27b-growpath:BF16
```

Lemonade

How to use Ssum-mer/qwen3.8-27b-growpath with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ssum-mer/qwen3.8-27b-growpath:BF16

Run and chat with the model

lemonade run user.qwen3.8-27b-growpath-BF16

List all available models

lemonade list

Hermes Agent

How to use Ssum-mer/qwen3.8-27b-growpath with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ssum-mer/qwen3.8-27b-growpath:BF16

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 Ssum-mer/qwen3.8-27b-growpath:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Ssum-mer/qwen3.8-27b-growpath with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ssum-mer/qwen3.8-27b-growpath:BF16

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 "Ssum-mer/qwen3.8-27b-growpath:BF16" \
  --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"

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GrowPath — Qwen3.8-27B · V18

Qwen3.8-27B를 기반으로 파인튜닝한 GrowPath 업무 학습 로드맵 생성 모델.

기본 모델에 LoRA 변경분을 병합한 전체 가중치입니다. 별도 LoRA 어댑터 적용 없이 병합 모델로 로드합니다.

모델 정보

항목	내용
기반 모델	Qwen/Qwen3.8-27B
기반 revision	`1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0`
최종 버전	GrowPath V18
최종 학습 에폭	2 · 제작자 확인
주요 용도	한국어 업무 학습 로드맵 생성·부분 수정
배포 형태	LoRA 병합 전체 모델·BF16·Safetensors 12샤드
파라미터	27,356,728,560
가중치 크기	54,713,457,120 bytes

아키텍처 표기

저장소와 기반 모델의 이름은 Qwen3.8-27B입니다. 저장된 config의 아키텍처 구현 이름은 Qwen3_5ForConditionalGeneration, model_type은 qwen3_5입니다. Hugging Face가 표시하는 qwen3_5 자동 태그는 이 config 필드에서 유래하며, 기반 저장소명과 구분합니다.

입력과 출력

업무 목표·현재 역량·기간·주당 학습시간·예산·학습 자료 등 제공된 조건을 입력으로 사용합니다. 로드맵과 부분 수정 요청의 구조화된 응답을 대상으로 파인튜닝했습니다. 출력된 기간·예산·자료 근거·수정 범위는 사용 전에 확인해야 합니다.

선정 배경

기존 모델보다 약 10% 우위라고 판단해 V18을 최종 선택했습니다. 업무 목적에 맞춘 답변 구성과 병합 모델의 배포·버전 관리 편의를 함께 고려했습니다. 10%는 제작자의 선정 판단이며, 이 모델 카드에서 새로 측정한 벤치마크 향상률을 뜻하지 않습니다.

사용 범위

업무 학습 계획 수립을 지원하는 모델입니다. 규정의 최신성·승인 상태와 추천 자료의 이용 가능성은 별도 검색·검증 경로에서 확인해야 합니다. 파인튜닝 모델 자체가 현재 DB나 최신 원문을 자동 조회하지는 않습니다.

BF16 GGUF

텍스트 생성용 BF16 GGUF입니다. 기존 Safetensors12샤드도 그대로 유지합니다.

파일: qwen3.8-27b-growpath-BF16.gguf
크기: 53,808,282,112 bytes
SHA256: 32d69322977ccd21240d4005a5b4cedb877702724c1159a57faa174f87e1cb81
변환 기록 · 체크섬
원본 모델: https://huggingface.co/Ssum-mer/qwen3.8-27b-growpath
4비트 모델: https://huggingface.co/Ssum-mer/qwen3.8-27b-growpath-Q4
모델 버전: V18 · 원본학습2에폭(제작자 확인)
원본 revision: 66d1af509ab0681f3b9365227e5c794c65801fbf

A100에서 모델 로딩·짧은 한국어 생성을 확인했습니다. 전체 품질 재평가 결과는 아닙니다. 이미지 입력용 vision projector는 포함하지 않습니다. 저장소명은 Qwen3.8이며 구현 아키텍처 이름은 qwen3_5입니다.

Downloads last month: 338

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for Ssum-mer/qwen3.8-27b-growpath

Base model

Qwen/Qwen3.8-27B

Finetuned

(772)

this model

Adapters

1 model

Quantizations

1 model