Instructions to use tellang/session-vault-qwen35-9b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tellang/session-vault-qwen35-9b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tellang/session-vault-qwen35-9b-gguf",
	filename="session-vault-9b-bf16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tellang/session-vault-qwen35-9b-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tellang/session-vault-qwen35-9b-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf tellang/session-vault-qwen35-9b-gguf:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tellang/session-vault-qwen35-9b-gguf:BF16
# Run inference directly in the terminal:
llama-cli -hf tellang/session-vault-qwen35-9b-gguf:BF16

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 tellang/session-vault-qwen35-9b-gguf:BF16
# Run inference directly in the terminal:
./llama-cli -hf tellang/session-vault-qwen35-9b-gguf:BF16

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 tellang/session-vault-qwen35-9b-gguf:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tellang/session-vault-qwen35-9b-gguf:BF16

Use Docker

docker model run hf.co/tellang/session-vault-qwen35-9b-gguf:BF16

LM Studio
Jan

vLLM

How to use tellang/session-vault-qwen35-9b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tellang/session-vault-qwen35-9b-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tellang/session-vault-qwen35-9b-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tellang/session-vault-qwen35-9b-gguf:BF16

Ollama
How to use tellang/session-vault-qwen35-9b-gguf with Ollama:
```
ollama run hf.co/tellang/session-vault-qwen35-9b-gguf:BF16
```

Unsloth Studio

How to use tellang/session-vault-qwen35-9b-gguf 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 tellang/session-vault-qwen35-9b-gguf 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 tellang/session-vault-qwen35-9b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tellang/session-vault-qwen35-9b-gguf to start chatting

How to use tellang/session-vault-qwen35-9b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tellang/session-vault-qwen35-9b-gguf:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "tellang/session-vault-qwen35-9b-gguf:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tellang/session-vault-qwen35-9b-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tellang/session-vault-qwen35-9b-gguf: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 tellang/session-vault-qwen35-9b-gguf:BF16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use tellang/session-vault-qwen35-9b-gguf with Docker Model Runner:
```
docker model run hf.co/tellang/session-vault-qwen35-9b-gguf:BF16
```

Lemonade

How to use tellang/session-vault-qwen35-9b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tellang/session-vault-qwen35-9b-gguf:BF16

Run and chat with the model

lemonade run user.session-vault-qwen35-9b-gguf-BF16

List all available models

lemonade list

session-vault-qwen35-9b-gguf

Qwen 3.5 9B를 한국어 개발 세션 요약 태스크에 LoRA 파인튜닝한 모델의 GGUF 양자화 버전.

학습 정보

항목	값
Base model	Qwen/Qwen3.5-9B
Method	LoRA 16-bit (r=32, alpha=64)
Hardware	NVIDIA H200 NVL x2 (287GB VRAM)
Dataset	196개 Claude 세션 요약 쌍 (avg quality 88.8)
Epochs	3
Loss	1.36 → 0.77
Training time	~530s
Quantization	Q4_K_M (llama.cpp)

태스크

Claude Code 세션 로그(raw markdown)를 구조화된 한국어 요약으로 변환:

YAML frontmatter (프로젝트, 태그, 유형)
본문 섹션: 목적 / 핵심 변경사항 / 결과 / 관련 파일

Ollama 사용법

# Modelfile
cat > Modelfile << 'EOF'
FROM ./session-vault-9b-q4_k_m.gguf
PARAMETER num_ctx 8192
PARAMETER num_predict 6144
PARAMETER temperature 0.7
PARAMETER top_p 0.8
PARAMETER top_k 20
PARAMETER repeat_penalty 1.0
EOF

ollama create session-vault:9b -f Modelfile
ollama run session-vault:9b

권장 파라미터

파라미터	값	비고
num_ctx	8192	4096은 타임아웃 유발
num_predict	6144	thinking 토큰 포함
temperature	0.7	Qwen 3.5 non-thinking 공식
top_p	0.8	공식 권장
top_k	20	공식 권장
repeat_penalty	1.0	공식: 항상 1.0
presence_penalty	1.5	/api/chat 전용
kv_cache_type	q8_0	VRAM 절감 (12GB GPU 권장)

학습 데이터

session-vault에서 자동 생성:

scripts/build_finetune_dataset.py: raw/summary 매칭 + 품질 필터링
에이전트/단기 세션 자동 제외, score >= 60 필터
Unsloth 호환 conversations 포맷 (system/user/assistant)

라이선스

Apache 2.0 (Qwen 3.5 라이선스 준수)

Downloads last month: 8

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

16-bit

Model tree for tellang/session-vault-qwen35-9b-gguf

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Adapter

(377)

this model