Instructions to use Kentucky-Open-Science/KOS-V4-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kentucky-Open-Science/KOS-V4-Instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="Kentucky-Open-Science/KOS-V4-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Kentucky-Open-Science/KOS-V4-Instruct-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Kentucky-Open-Science/KOS-V4-Instruct-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 Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

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 Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

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 Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Kentucky-Open-Science/KOS-V4-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kentucky-Open-Science/KOS-V4-Instruct-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": "Kentucky-Open-Science/KOS-V4-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

SGLang

How to use Kentucky-Open-Science/KOS-V4-Instruct-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 "Kentucky-Open-Science/KOS-V4-Instruct-GGUF" \
    --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": "Kentucky-Open-Science/KOS-V4-Instruct-GGUF",
		"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 "Kentucky-Open-Science/KOS-V4-Instruct-GGUF" \
        --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": "Kentucky-Open-Science/KOS-V4-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Kentucky-Open-Science/KOS-V4-Instruct-GGUF with Ollama:
```
ollama run hf.co/Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use Kentucky-Open-Science/KOS-V4-Instruct-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 Kentucky-Open-Science/KOS-V4-Instruct-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 Kentucky-Open-Science/KOS-V4-Instruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Kentucky-Open-Science/KOS-V4-Instruct-GGUF to start chatting

How to use Kentucky-Open-Science/KOS-V4-Instruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

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": "Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Kentucky-Open-Science/KOS-V4-Instruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

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 Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use Kentucky-Open-Science/KOS-V4-Instruct-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

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 "Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M" \
  --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"

Docker Model Runner
How to use Kentucky-Open-Science/KOS-V4-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use Kentucky-Open-Science/KOS-V4-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Kentucky-Open-Science/KOS-V4-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.KOS-V4-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

KOS-V4-Instruct-GGUF / testing /run_quant_ifeval.sh

codybum

Upload testing/run_quant_ifeval.sh with huggingface_hub

2e13348 verified 24 days ago

Raw

History Blame Contribute Delete

1.29 kB

	#!/usr/bin/env bash
	# Launch llama-server for a GGUF, wait until ready, run official lm-eval ifeval
	# (apply_chat_template, client-side pristine tokenizer), then kill the server.
	# run_quant_ifeval.sh <gguf> <label> <port> <gpu>
	set -u
	GGUF="$1"; LABEL="$2"; PORT="$3"; GPU="$4"
	SRV=/workspace/llm/llama.cpp/build/bin/llama-server
	SCR=/tmp/claude-0/-workspace/f1993a73-9699-445b-818e-eb56628e7541/scratchpad
	SRVLOG="$SCR/srv_${LABEL}.log"

	CUDA_VISIBLE_DEVICES="$GPU" "$SRV" -m "$GGUF" --host 127.0.0.1 --port "$PORT" \
	--alias kosv4 -ngl 99 -c 8192 -np 4 -t 6 > "$SRVLOG" 2>&1 &
	SRVPID=$!
	echo "[$LABEL] server pid=$SRVPID gpu=$GPU port=$PORT gguf=$(basename "$GGUF")"

	# wait for /health ok (up to 120s)
	ok=0
	for i in $(seq 1 120); do
	if curl -s "http://127.0.0.1:$PORT/health" 2>/dev/null \| grep -q '"status":"ok"'; then ok=1; break; fi
	if ! kill -0 "$SRVPID" 2>/dev/null; then echo "[$LABEL] server died early"; tail -20 "$SRVLOG"; exit 1; fi
	sleep 1
	done
	[ "$ok" = 1 ] \|\| { echo "[$LABEL] server not ready"; tail -20 "$SRVLOG"; kill "$SRVPID" 2>/dev/null; exit 1; }
	echo "[$LABEL] server ready after ~${i}s"

	cd "$SCR"
	python3 run_lmeval_gguf.py "$PORT" "$LABEL"
	RC=$?
	kill "$SRVPID" 2>/dev/null
	wait "$SRVPID" 2>/dev/null
	echo "[$LABEL] done rc=$RC, server stopped"
	exit $RC