Instructions to use ApprikatAI/AMD-Llama-135m-code-FP16-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ApprikatAI/AMD-Llama-135m-code-FP16-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ApprikatAI/AMD-Llama-135m-code-FP16-GGUF",
	filename="amd-llama-135m-code-fp16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ApprikatAI/AMD-Llama-135m-code-FP16-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ApprikatAI/AMD-Llama-135m-code-FP16-GGUF
# Run inference directly in the terminal:
llama-cli -hf ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ApprikatAI/AMD-Llama-135m-code-FP16-GGUF
# Run inference directly in the terminal:
llama-cli -hf ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

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 ApprikatAI/AMD-Llama-135m-code-FP16-GGUF
# Run inference directly in the terminal:
./llama-cli -hf ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

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 ApprikatAI/AMD-Llama-135m-code-FP16-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

Use Docker

docker model run hf.co/ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

LM Studio
Jan
Ollama
How to use ApprikatAI/AMD-Llama-135m-code-FP16-GGUF with Ollama:
```
ollama run hf.co/ApprikatAI/AMD-Llama-135m-code-FP16-GGUF
```

Unsloth Studio new

How to use ApprikatAI/AMD-Llama-135m-code-FP16-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 ApprikatAI/AMD-Llama-135m-code-FP16-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 ApprikatAI/AMD-Llama-135m-code-FP16-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ApprikatAI/AMD-Llama-135m-code-FP16-GGUF to start chatting

Docker Model Runner
How to use ApprikatAI/AMD-Llama-135m-code-FP16-GGUF with Docker Model Runner:
```
docker model run hf.co/ApprikatAI/AMD-Llama-135m-code-FP16-GGUF
```

Lemonade

How to use ApprikatAI/AMD-Llama-135m-code-FP16-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

Run and chat with the model

lemonade run user.AMD-Llama-135m-code-FP16-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

This model was converted to GGUF format from amd/AMD-Llama-135m-code using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo ApprikatAI/AMD-Llama-135m-code-FP16-GGUF --hf-file amd-llama-135m-code-fp16.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo ApprikatAI/AMD-Llama-135m-code-FP16-GGUF --hf-file amd-llama-135m-code-fp16.gguf -c 2048

Downloads last month: 2

GGUF

Model size

0.1B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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

Model tree for ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

Base model

amd/AMD-Llama-135m-code

Quantized

(11)

this model

ApprikatAI
/

AMD-Llama-135m-code-FP16-GGUF

ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

Use with llama.cpp

CLI:

Server:

Model tree for ApprikatAI/AMD-Llama-135m-code-FP16-GGUF

Dataset used to train ApprikatAI/AMD-Llama-135m-code-FP16-GGUF