Instructions to use second-state/Llama-3-Instruct-8B-SimPO-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/Llama-3-Instruct-8B-SimPO-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="second-state/Llama-3-Instruct-8B-SimPO-GGUF")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("second-state/Llama-3-Instruct-8B-SimPO-GGUF")
model = AutoModelForCausalLM.from_pretrained("second-state/Llama-3-Instruct-8B-SimPO-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use second-state/Llama-3-Instruct-8B-SimPO-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 second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/Llama-3-Instruct-8B-SimPO-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 second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf second-state/Llama-3-Instruct-8B-SimPO-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 second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/Llama-3-Instruct-8B-SimPO-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 second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use second-state/Llama-3-Instruct-8B-SimPO-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "second-state/Llama-3-Instruct-8B-SimPO-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "second-state/Llama-3-Instruct-8B-SimPO-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M

SGLang

How to use second-state/Llama-3-Instruct-8B-SimPO-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 "second-state/Llama-3-Instruct-8B-SimPO-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": "second-state/Llama-3-Instruct-8B-SimPO-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 "second-state/Llama-3-Instruct-8B-SimPO-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": "second-state/Llama-3-Instruct-8B-SimPO-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use second-state/Llama-3-Instruct-8B-SimPO-GGUF with Ollama:
```
ollama run hf.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use second-state/Llama-3-Instruct-8B-SimPO-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M
```

Lemonade

How to use second-state/Llama-3-Instruct-8B-SimPO-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/Llama-3-Instruct-8B-SimPO-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3-Instruct-8B-SimPO-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Llama-3-Instruct-8B-SimPO-GGUF

Original Model

princeton-nlp/Llama-3-Instruct-8B-SimPO

Run with LlamaEdge

LlamaEdge version: v0.11.2

Prompt template

Prompt type: llama-3-chat

Prompt string

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Context size: 4096

Run as LlamaEdge service

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf \
  llama-api-server.wasm \
  --prompt-template llama-3-chat \
  --ctx-size 4096 \
  --model-name Llama-3-8b

Run as LlamaEdge command app

wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf \
  llama-chat.wasm \
  --prompt-template llama-3-chat \
  --ctx-size 4096

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
Llama-3-Instruct-8B-SimPO-Q2_K.gguf	Q2_K	2	3.18 GB	smallest, significant quality loss - not recommended for most purposes
Llama-3-Instruct-8B-SimPO-Q3_K_L.gguf	Q3_K_L	3	4.32 GB	small, substantial quality loss
Llama-3-Instruct-8B-SimPO-Q3_K_M.gguf	Q3_K_M	3	4.02 GB	very small, high quality loss
Llama-3-Instruct-8B-SimPO-Q3_K_S.gguf	Q3_K_S	3	3.66 GB	very small, high quality loss
Llama-3-Instruct-8B-SimPO-Q4_0.gguf	Q4_0	4	4.66 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Llama-3-Instruct-8B-SimPO-Q4_K_M.gguf	Q4_K_M	4	4.92 GB	medium, balanced quality - recommended
Llama-3-Instruct-8B-SimPO-Q4_K_S.gguf	Q4_K_S	4	4.69 GB	small, greater quality loss
Llama-3-Instruct-8B-SimPO-Q5_0.gguf	Q5_0	5	5.6 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Llama-3-Instruct-8B-SimPO-Q5_K_M.gguf	Q5_K_M	5	5.73 GB	large, very low quality loss - recommended
Llama-3-Instruct-8B-SimPO-Q5_K_S.gguf	Q5_K_S	5	5.6 GB	large, low quality loss - recommended
Llama-3-Instruct-8B-SimPO-Q6_K.gguf	Q6_K	6	6.6 GB	very large, extremely low quality loss
Llama-3-Instruct-8B-SimPO-Q8_0.gguf	Q8_0	8	8.54 GB	very large, extremely low quality loss - not recommended
Llama-3-Instruct-8B-SimPO-f16.gguf	f16	16	16.1 GB

Quantized with llama.cpp b2963.

Downloads last month: 257

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for second-state/Llama-3-Instruct-8B-SimPO-GGUF

Base model

princeton-nlp/Llama-3-Instruct-8B-SimPO

Quantized

(12)

this model