Instructions to use csala/ALIA-40b-Q3_K-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use csala/ALIA-40b-Q3_K-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="csala/ALIA-40b-Q3_K-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("csala/ALIA-40b-Q3_K-GGUF", dtype="auto")

llama-cpp-python

How to use csala/ALIA-40b-Q3_K-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="csala/ALIA-40b-Q3_K-GGUF",
	filename="ALIA-40b.Q3_K.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 csala/ALIA-40b-Q3_K-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf csala/ALIA-40b-Q3_K-GGUF
# Run inference directly in the terminal:
llama-cli -hf csala/ALIA-40b-Q3_K-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf csala/ALIA-40b-Q3_K-GGUF
# Run inference directly in the terminal:
llama-cli -hf csala/ALIA-40b-Q3_K-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 csala/ALIA-40b-Q3_K-GGUF
# Run inference directly in the terminal:
./llama-cli -hf csala/ALIA-40b-Q3_K-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 csala/ALIA-40b-Q3_K-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf csala/ALIA-40b-Q3_K-GGUF

Use Docker

docker model run hf.co/csala/ALIA-40b-Q3_K-GGUF

LM Studio
Jan

vLLM

How to use csala/ALIA-40b-Q3_K-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "csala/ALIA-40b-Q3_K-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "csala/ALIA-40b-Q3_K-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/csala/ALIA-40b-Q3_K-GGUF

SGLang

How to use csala/ALIA-40b-Q3_K-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 "csala/ALIA-40b-Q3_K-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": "csala/ALIA-40b-Q3_K-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 "csala/ALIA-40b-Q3_K-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": "csala/ALIA-40b-Q3_K-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use csala/ALIA-40b-Q3_K-GGUF with Ollama:
```
ollama run hf.co/csala/ALIA-40b-Q3_K-GGUF
```

Unsloth Studio new

How to use csala/ALIA-40b-Q3_K-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 csala/ALIA-40b-Q3_K-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 csala/ALIA-40b-Q3_K-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for csala/ALIA-40b-Q3_K-GGUF to start chatting

Docker Model Runner
How to use csala/ALIA-40b-Q3_K-GGUF with Docker Model Runner:
```
docker model run hf.co/csala/ALIA-40b-Q3_K-GGUF
```

Lemonade

How to use csala/ALIA-40b-Q3_K-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull csala/ALIA-40b-Q3_K-GGUF

Run and chat with the model

lemonade run user.ALIA-40b-Q3_K-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

ALIA-40b in GGUF format and quantized to `Q3_K`

ALIA-40B is a 40B parameter base language model developed by the Barcelona Supercomputing Center (BSC).

Original model and details here: https://huggingface.co/BSC-LT/ALIA-40b

This model is released under a permissive Apache 2.0 license. Along with the open weights, all training scripts and configuration files are made publicly available in this GitHub repository.

This repository contains the model in GGUF format and afterwards quantized to Q3_K level using llama.cpp.

Model Details

Description

Transformer-based decoder-only language model that has been pre-trained from scratch on 9.37 trillion tokens of highly curated data. The pre-training corpus contains text in 35 European languages and code.

Hyperparameters

The full list of hyperparameters can be found here.

Architecture


Total Parameters	40,433,885,184
Embedding Parameters	2,097,152,000
Layers	48
Hidden size	8,192
Attention heads	64
Context length	32,768
Vocabulary size	256,000
Precision	bfloat16
Embedding type	RoPE
Activation Function	SwiGLU
Layer normalization	RMS Norm
Flash attention	✅
Grouped Query Attention	✅
Num. query groups	8

Conversion Process

There are the steps that were followed to convert the weights to GGUF format and quantize.

1. Download from HuggingFace

Requirement: huggingface_hub

huggingface-cli download --cache-dir . BSC-LT/ALIA-40b

This command downloads the model into the directory ./models--BSC-LT--ALIA-40b/

The safetensors files end up inside ./models--BSC-LT--ALIA-40b/snapshots/aa8a4ac7f9e18f3c2ea8ec0cc84e7783cd751ac7/.

2. Convert Safetensors to GUFF without quantization using llama.cpp

Requirement: llama.cpp repository and python requirements installed.

cd $LLAMA_PATH
python convert_hf_to_gguf.py $ALIA_PATH/models--BSC-LT--ALIA-40b/snapshots/aa8a4ac7f9e18f3c2ea8ec0cc84e7783cd751ac7/ --outfile $ALIA_PATH/ALIA-40B.gguf

LLAMA_PATH is the root of the llama.cpp directory. ALIA_PATH is the directory where we downloaded the Safetensors weights and where we want to store the ALIA-40B GGUF file.

This creates the file $ALIA_PATH/ALIA-40B.gguf.

3. Quantize the model

Requirement: llama.cpp built and installed.

cd $ALIA_PATH
llama-quantize ALIA-40B.gguf ALIA-40B.Q3_K.gguf Q3_K

This generates the file ALIA-40B.Q3_K.gguf within the same directory.

Downloads last month: 5

GGUF

Model size

40B params

Architecture

llama

Hardware compatibility

Model tree for csala/ALIA-40b-Q3_K-GGUF

Base model

BSC-LT/ALIA-40b

Quantized

(12)

this model

csala
/

ALIA-40b-Q3_K-GGUF

ALIA-40b in GGUF format and quantized to `Q3_K`

Model Details

Description

Hyperparameters

Architecture

Conversion Process

1. Download from HuggingFace

2. Convert Safetensors to GUFF without quantization using llama.cpp

3. Quantize the model

Model tree for csala/ALIA-40b-Q3_K-GGUF

Datasets used to train csala/ALIA-40b-Q3_K-GGUF

ALIA-40b in GGUF format and quantized to Q3_K

Model Details

Description

Hyperparameters

Architecture

Conversion Process

1. Download from HuggingFace

2. Convert Safetensors to GUFF without quantization using llama.cpp

3. Quantize the model

Model tree for csala/ALIA-40b-Q3_K-GGUF

Datasets used to train csala/ALIA-40b-Q3_K-GGUF

ALIA-40b in GGUF format and quantized to `Q3_K`