Instructions to use second-state/moxin-instruct-7b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use second-state/moxin-instruct-7b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="second-state/moxin-instruct-7b-GGUF",
	filename="moxin-instruct-7b-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use second-state/moxin-instruct-7b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf second-state/moxin-instruct-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/moxin-instruct-7b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf second-state/moxin-instruct-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf second-state/moxin-instruct-7b-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/moxin-instruct-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf second-state/moxin-instruct-7b-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/moxin-instruct-7b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf second-state/moxin-instruct-7b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/second-state/moxin-instruct-7b-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use second-state/moxin-instruct-7b-GGUF with Ollama:
```
ollama run hf.co/second-state/moxin-instruct-7b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use second-state/moxin-instruct-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 second-state/moxin-instruct-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 second-state/moxin-instruct-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 second-state/moxin-instruct-7b-GGUF to start chatting

Docker Model Runner
How to use second-state/moxin-instruct-7b-GGUF with Docker Model Runner:
```
docker model run hf.co/second-state/moxin-instruct-7b-GGUF:Q4_K_M
```

Lemonade

How to use second-state/moxin-instruct-7b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull second-state/moxin-instruct-7b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.moxin-instruct-7b-GGUF-Q4_K_M

List all available models

lemonade list

moxin-instruct-7b-GGUF

Original Model

moxin-org/moxin-instruct-7b

Run with LlamaEdge

LlamaEdge version: v0.20.0

Prompt template

Prompt type: moxin-instruct

Prompt string

<|system|>
{system_message}
<|user|>
{user_message_1}
<|assistant|>
{assistant_message_1}<|endoftext|>
<|user|>
{user_message_2}
<|assistant|>

Context size: 32000

Run as LlamaEdge service

wasmedge --dir .:. \
  --nn-preload default:GGML:AUTO:moxin-instruct-7b-Q5_K_M.gguf \
  llama-api-server.wasm \
  --model-name moxin-instruct-7b \
  --prompt-template moxin-instruct \
  --ctx-size 32000

Quantized GGUF Models

Name	Quant method	Bits	Size	Use case
moxin-instruct-7b-Q2_K.gguf	Q2_K	2	3.04 GB	smallest, significant quality loss - not recommended for most purposes
moxin-instruct-7b-Q3_K_L.gguf	Q3_K_L	3	4.28 GB	small, substantial quality loss
moxin-instruct-7b-Q3_K_M.gguf	Q3_K_M	3	3.94 GB	very small, high quality loss
moxin-instruct-7b-Q3_K_S.gguf	Q3_K_S	3	3.54 GB	very small, high quality loss
moxin-instruct-7b-Q4_0.gguf	Q4_0	4	4.60 GB	legacy; small, very high quality loss - prefer using Q3_K_M
moxin-instruct-7b-Q4_K_M.gguf	Q4_K_M	4	4.89 GB	medium, balanced quality - recommended
moxin-instruct-7b-Q4_K_S.gguf	Q4_K_S	4	4.63 GB	small, greater quality loss
moxin-instruct-7b-Q5_0.gguf	Q5_0	5	5.60 GB	legacy; medium, balanced quality - prefer using Q4_K_M
moxin-instruct-7b-Q5_K_M.gguf	Q5_K_M	5	5.75 GB	large, very low quality loss - recommended
moxin-instruct-7b-Q5_K_S.gguf	Q5_K_S	5	5.60 GB	large, low quality loss - recommended
moxin-instruct-7b-Q6_K.gguf	Q6_K	6	6.66 GB	very large, extremely low quality loss
moxin-instruct-7b-Q8_0.gguf	Q8_0	8	8.62 GB	very large, extremely low quality loss - not recommended
moxin-instruct-7b-f16.gguf	f16	16	16.2 GB

Quantized with llama.cpp b5410

Downloads last month: 129

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for second-state/moxin-instruct-7b-GGUF

Base model

moxin-org/Moxin-7B-Instruct

Quantized

(5)

this model