Instructions to use duyntnet/ALMA-13B-R-imatrix-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use duyntnet/ALMA-13B-R-imatrix-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="duyntnet/ALMA-13B-R-imatrix-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("duyntnet/ALMA-13B-R-imatrix-GGUF", dtype="auto")

llama-cpp-python

How to use duyntnet/ALMA-13B-R-imatrix-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="duyntnet/ALMA-13B-R-imatrix-GGUF",
	filename="ALMA-13B-R-IQ1_M.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 duyntnet/ALMA-13B-R-imatrix-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf duyntnet/ALMA-13B-R-imatrix-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 duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf duyntnet/ALMA-13B-R-imatrix-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 duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf duyntnet/ALMA-13B-R-imatrix-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 duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M

Use Docker

docker model run hf.co/duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use duyntnet/ALMA-13B-R-imatrix-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "duyntnet/ALMA-13B-R-imatrix-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "duyntnet/ALMA-13B-R-imatrix-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M

SGLang

How to use duyntnet/ALMA-13B-R-imatrix-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 "duyntnet/ALMA-13B-R-imatrix-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": "duyntnet/ALMA-13B-R-imatrix-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 "duyntnet/ALMA-13B-R-imatrix-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": "duyntnet/ALMA-13B-R-imatrix-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use duyntnet/ALMA-13B-R-imatrix-GGUF with Ollama:
```
ollama run hf.co/duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M
```

Unsloth Studio new

How to use duyntnet/ALMA-13B-R-imatrix-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 duyntnet/ALMA-13B-R-imatrix-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 duyntnet/ALMA-13B-R-imatrix-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for duyntnet/ALMA-13B-R-imatrix-GGUF to start chatting

Docker Model Runner
How to use duyntnet/ALMA-13B-R-imatrix-GGUF with Docker Model Runner:
```
docker model run hf.co/duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M
```

Lemonade

How to use duyntnet/ALMA-13B-R-imatrix-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull duyntnet/ALMA-13B-R-imatrix-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ALMA-13B-R-imatrix-GGUF-Q4_K_M

List all available models

lemonade list

Quantizations of https://huggingface.co/haoranxu/ALMA-13B-R

From original readme

A quick start to use our best system (ALMA-13B-R) for translation. An example of translating "我爱机器翻译。" into English:

import torch
from transformers import AutoModelForCausalLM
from transformers import AutoTokenizer

# Load base model and LoRA weights
model = AutoModelForCausalLM.from_pretrained("haoranxu/ALMA-13B-R", torch_dtype=torch.float16, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("haoranxu/ALMA-13B-R", padding_side='left')

# Add the source sentence into the prompt template
prompt="Translate this from Chinese to English:\nChinese: 我爱机器翻译。\nEnglish:"
input_ids = tokenizer(prompt, return_tensors="pt", padding=True, max_length=40, truncation=True).input_ids.cuda()

# Translation
with torch.no_grad():
    generated_ids = model.generate(input_ids=input_ids, num_beams=5, max_new_tokens=20, do_sample=True, temperature=0.6, top_p=0.9)
outputs = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
print(outputs)

Downloads last month: 39

GGUF

Model size

13B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit