Instructions to use PLTAT/Filipino_llama_3.1_FT_8B_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PLTAT/Filipino_llama_3.1_FT_8B_GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PLTAT/Filipino_llama_3.1_FT_8B_GGUF",
	filename="llama-3.1-8b.Q8_0.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 PLTAT/Filipino_llama_3.1_FT_8B_GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0

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 PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0

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 PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0

Use Docker

docker model run hf.co/PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0

LM Studio
Jan
Ollama
How to use PLTAT/Filipino_llama_3.1_FT_8B_GGUF with Ollama:
```
ollama run hf.co/PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0
```

Unsloth Studio new

How to use PLTAT/Filipino_llama_3.1_FT_8B_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 PLTAT/Filipino_llama_3.1_FT_8B_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 PLTAT/Filipino_llama_3.1_FT_8B_GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PLTAT/Filipino_llama_3.1_FT_8B_GGUF to start chatting

Docker Model Runner
How to use PLTAT/Filipino_llama_3.1_FT_8B_GGUF with Docker Model Runner:
```
docker model run hf.co/PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0
```

Lemonade

How to use PLTAT/Filipino_llama_3.1_FT_8B_GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PLTAT/Filipino_llama_3.1_FT_8B_GGUF:Q8_0

Run and chat with the model

lemonade run user.Filipino_llama_3.1_FT_8B_GGUF-Q8_0

List all available models

lemonade list

welyjesch commited on Mar 26

Commit

0c0530a

verified ·

1 Parent(s): f71c5f7

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -70,7 +70,7 @@ Below is an instruction that describes a task, paired with an input that provide
 ---
 ## 🚀 How to use for Inference in Google Colab
-You can easily use the lora version of this through Unsloth, which is faster and easier, because I've provided a python notebook you can open in Colab:[Filipino Llama 3.1 Inference Notebook](https://huggingface.co/welyjesch/filipino_llama_3.1_finetuned_lora/blob/main/Filipino_Llama3_1.ipynb)
 You can easily run this GGUF model in the free tier of Google Colab using `llama-cpp-python` with hardware acceleration.

 ---
 ## 🚀 How to use for Inference in Google Colab
+You can easily use the lora version of this through Unsloth, which is faster and easier, because I've provided a python notebook you can open in Colab:[Filipino Llama 3.1 Inference Notebook](https://huggingface.co/welyjesch/filipino_llama_3.1_FT_8B_GGUF/blob/main/Filipino_Llama3_1_Inference_Only.ipynb)
 You can easily run this GGUF model in the free tier of Google Colab using `llama-cpp-python` with hardware acceleration.