Instructions to use ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF")
model = AutoModelForCausalLM.from_pretrained("ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ciphermosaic/Llama-3.2-1B-code-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": "ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M

SGLang

How to use ciphermosaic/Llama-3.2-1B-code-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 "ciphermosaic/Llama-3.2-1B-code-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": "ciphermosaic/Llama-3.2-1B-code-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 "ciphermosaic/Llama-3.2-1B-code-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": "ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF with Ollama:
```
ollama run hf.co/ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M
```

Unsloth Studio

How to use ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF to start chatting

How to use ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-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": "ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-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 "ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Llama-3.2-1B-code-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-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 ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

Llama-3.2-1B-code-Instruct-GGUF / README.md

ciphermosaic

Update README.md

77a3029 verified 26 days ago

preview code

Raw

History Blame Contribute Delete

4.43 kB

	---
	license: llama3.2
	base_model: meta-llama/Llama-3.2-1B-Instruct
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- llama
	- llama-3.2
	- code
	- coding-assistant
	- instruct
	- gguf
	- unsloth
	- transformers
	- ollama
	language:
	- en
	---

	# Llama-3.2-1B-Code-Instruct-GGUF

	A lightweight coding assistant fine tuned from Meta Llama 3.2 1B Instruct on the CodeAlpaca-20K dataset. The model is optimized for instruction following in programming related tasks such as code generation, debugging, explaining code, and answering software development questions.

	The model was fine tuned using Unsloth for efficient training and merged into a standalone checkpoint before being converted to GGUF for local inference with Ollama and llama.cpp compatible runtimes.

	## Model Details

	\| Property \| Value \|
	\| --------------------- \| ------------------------------- \|
	\| Model \| Llama-3.2-1B-Code-Instruct-GGUF \|
	\| Author \| ciphermosaic \|
	\| Base Model \| Meta Llama-3.2-1B-Instruct \|
	\| Fine Tuning Framework \| Unsloth \|
	\| Dataset \| sahil2801/codeAlpaca-20k \|
	\| Quantization \| GGUF Q4_K_M \|
	\| Intended Use \| Coding Assistant \|

	## Training

	The model was instruction tuned on the complete CodeAlpaca-20K dataset.

	### Training Configuration

	* Framework: Unsloth
	* Precision: FP16
	* 4-bit Loading: Enabled
	* Per Device Batch Size: 2
	* Gradient Accumulation Steps: 4
	* Learning Rate: 2e-5
	* Logging Steps: 25
	* Save Strategy: Every Epoch

	## Dataset

	Training was performed using:

	Dataset: `sahil2801/codeAlpaca-20k`

	The dataset contains instruction and response pairs covering various programming tasks including:

	* Code generation
	* Code explanation
	* Debugging
	* Algorithm implementation
	* Programming concepts
	* Multiple programming languages

	## Capabilities

	The model performs well on tasks such as:

	* Writing Python, C++, Java, JavaScript, and other programming languages
	* Explaining existing code
	* Debugging common programming errors
	* Implementing algorithms and data structures
	* Generating functions from natural language instructions
	* Answering programming related questions

	## Prompt Format

	The model follows the Llama instruction format.

	Example

	```text
	### Instruction:
	Write a Python function to check if a string is a palindrome.

	### Response:
	```

	## Running with Transformers

	```python
	from transformers import AutoTokenizer, AutoModelForCausalLM

	model_id = "ciphermosaic/Llama-3.2-1B-code-Instruct-GGUF"

	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(model_id)

	prompt = "Write a Python function to reverse a linked list."

	inputs = tokenizer(prompt, return_tensors="pt")

	outputs = model.generate(**inputs, max_new_tokens=256)

	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```

	## Running with Ollama

	After downloading the GGUF model, create a Modelfile:

	```text
	FROM ./Llama-3.2-1B-Code-Instruct-Q4_K_M.gguf
	```

	Create the model:

	```bash
	ollama create llama32-code -f Modelfile
	```

	Run:

	```bash
	ollama run llama32-code
	```



	## Ollama Demo

	![Ollama Demo](Ollama_test.png)



	## GGUF

	This repository includes a GGUF version using:

	* Q4_K_M

	Compatible with:

	* Ollama
	* llama.cpp
	* LM Studio
	* Jan
	* Open WebUI

	## Limitations

	* Designed primarily for coding related tasks.
	* May generate incorrect or non optimal solutions for complex programming problems.
	* Responses should be reviewed before use in production environments.
	* Performance depends on prompt quality and task complexity.

	## Intended Use

	This model is intended for:

	* Learning programming
	* Code generation
	* Debugging
	* Software development assistance
	* Educational use
	* Local AI coding assistants

	It is not intended for safety critical or production systems without human verification.

	## Acknowledgements

	* Meta AI for the Llama 3.2 base model.
	* Unsloth for efficient fine tuning.
	* Hugging Face for model hosting and ecosystem.
	* sahil2801 for the CodeAlpaca-20K dataset.

	## License

	This model is derived from Meta Llama 3.2 and is distributed under the Llama 3.2 Community License. Please ensure compliance with the original license terms when using or redistributing this model.