Instructions to use tensorblock/upstage_llama-30b-instruct-2048-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tensorblock/upstage_llama-30b-instruct-2048-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/upstage_llama-30b-instruct-2048-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/upstage_llama-30b-instruct-2048-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/upstage_llama-30b-instruct-2048-GGUF:Q2_K
# Run inference directly in the terminal:
llama cli -hf tensorblock/upstage_llama-30b-instruct-2048-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/upstage_llama-30b-instruct-2048-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/upstage_llama-30b-instruct-2048-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/upstage_llama-30b-instruct-2048-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/upstage_llama-30b-instruct-2048-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/upstage_llama-30b-instruct-2048-GGUF:Q2_K

LM Studio
Jan

vLLM

How to use tensorblock/upstage_llama-30b-instruct-2048-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorblock/upstage_llama-30b-instruct-2048-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/upstage_llama-30b-instruct-2048-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tensorblock/upstage_llama-30b-instruct-2048-GGUF:Q2_K

Ollama
How to use tensorblock/upstage_llama-30b-instruct-2048-GGUF with Ollama:
```
ollama run hf.co/tensorblock/upstage_llama-30b-instruct-2048-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/upstage_llama-30b-instruct-2048-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/upstage_llama-30b-instruct-2048-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/upstage_llama-30b-instruct-2048-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/upstage_llama-30b-instruct-2048-GGUF to start chatting

Docker Model Runner
How to use tensorblock/upstage_llama-30b-instruct-2048-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/upstage_llama-30b-instruct-2048-GGUF:Q2_K
```

Lemonade

How to use tensorblock/upstage_llama-30b-instruct-2048-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/upstage_llama-30b-instruct-2048-GGUF:Q2_K

Run and chat with the model

lemonade run user.upstage_llama-30b-instruct-2048-GGUF-Q2_K

List all available models

lemonade list

Atomic Chat

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4bfc929166a0b7316b678ddf6c88980ff9384fcd51d921bcf28e8b2e6f90472d
-size 17279760064

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8f64e0a6d0c1750eb1ea5f64a4392e668d6505ac6d85dec8b861528aa4e31a11
-size 14064113344

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:14cf6f82d2002f219c68d5244b82c6ad96ae5e9165840a531d527591b117432d
-size 18355968704

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8cc2f4e634b2be4629da4b4da55ac06b10a734644ee8ec71a891ab49148565e2
-size 19621141184

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cabca166855551664d3b1bf3e7cea40c0ec451a6828c1653d9f42be2d8b9bbd3
-size 18482485952

tensorblock
/

upstage_llama-30b-instruct-2048-GGUF

Keep Q2_K/Q3_K_M gguf only