Instructions to use tensorblock/ko-ref-llama2-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/ko-ref-llama2-7b-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="tensorblock/ko-ref-llama2-7b-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/ko-ref-llama2-7b-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/ko-ref-llama2-7b-GGUF 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 tensorblock/ko-ref-llama2-7b-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/ko-ref-llama2-7b-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tensorblock/ko-ref-llama2-7b-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/ko-ref-llama2-7b-GGUF:Q2_K

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 tensorblock/ko-ref-llama2-7b-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/ko-ref-llama2-7b-GGUF:Q2_K

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 tensorblock/ko-ref-llama2-7b-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/ko-ref-llama2-7b-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/ko-ref-llama2-7b-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/ko-ref-llama2-7b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/ko-ref-llama2-7b-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/ko-ref-llama2-7b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tensorblock/ko-ref-llama2-7b-GGUF:Q2_K

SGLang

How to use tensorblock/ko-ref-llama2-7b-GGUF 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 "tensorblock/ko-ref-llama2-7b-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/ko-ref-llama2-7b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "tensorblock/ko-ref-llama2-7b-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorblock/ko-ref-llama2-7b-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use tensorblock/ko-ref-llama2-7b-GGUF with Ollama:
```
ollama run hf.co/tensorblock/ko-ref-llama2-7b-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/ko-ref-llama2-7b-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 tensorblock/ko-ref-llama2-7b-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 tensorblock/ko-ref-llama2-7b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/ko-ref-llama2-7b-GGUF to start chatting

Docker Model Runner
How to use tensorblock/ko-ref-llama2-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/ko-ref-llama2-7b-GGUF:Q2_K
```

Lemonade

How to use tensorblock/ko-ref-llama2-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/ko-ref-llama2-7b-GGUF:Q2_K

Run and chat with the model

lemonade run user.ko-ref-llama2-7b-GGUF-Q2_K

List all available models

lemonade list

Atomic Chat

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65f51850e2783f0ba26871427f871db5f23ca39678e2bcf98547c995267ac3eb
-size 3597111392

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2f25144c3f85fb5f5714f30f931de53e71e0fe4ba53dfbc53b6912e1a5c1c627
-size 3298005088

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ea50d03846c3afcfcc8db05f4ca99dba433889c5340733357b58df8538fca5e8
-size 2948304992

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7eefa55fde526243a24fb05420c55ecc32aa24ae99daaf47a2b66f84083e5dd7
-size 3825807456

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:46d80324efb77b2970a4817be6d2c207daca3766ccd50fae564bf827da298cfe
-size 4081004640

tensorblock
/

ko-ref-llama2-7b-GGUF

Remove .gguf files (keep Q2_K.gguf)