Instructions to use avans06/ALMA-13B-ct2-int8_float16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use avans06/ALMA-13B-ct2-int8_float16 with Transformers:

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

pipe = pipeline("text-generation", model="avans06/ALMA-13B-ct2-int8_float16")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("avans06/ALMA-13B-ct2-int8_float16", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use avans06/ALMA-13B-ct2-int8_float16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "avans06/ALMA-13B-ct2-int8_float16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "avans06/ALMA-13B-ct2-int8_float16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/avans06/ALMA-13B-ct2-int8_float16

SGLang

How to use avans06/ALMA-13B-ct2-int8_float16 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 "avans06/ALMA-13B-ct2-int8_float16" \
    --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": "avans06/ALMA-13B-ct2-int8_float16",
		"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 "avans06/ALMA-13B-ct2-int8_float16" \
        --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": "avans06/ALMA-13B-ct2-int8_float16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use avans06/ALMA-13B-ct2-int8_float16 with Docker Model Runner:
```
docker model run hf.co/avans06/ALMA-13B-ct2-int8_float16
```

ALMA-13B model for CTranslate2

The model is quantized version of the haoranxu/ALMA-13B with int8_float16 quantization and can be used in CTranslate2.

ALMA (Advanced Language Model-based trAnslator) is an LLM-based translation model, which adopts a new translation model paradigm: it begins with fine-tuning on monolingual data and is further optimized using high-quality parallel data. This two-step fine-tuning process ensures strong translation performance.

Model creator: Haoran Xu
Original model: ALMA 13B

Conversion details

The original model was converted on 2023-12 with the following command:

ct2-transformers-converter --model haoranxu/ALMA-13B --quantization int8_float16 --output_dir ALMA-13B-ct2-int8_float16 \
    --copy_files generation_config.json special_tokens_map.json tokenizer.model tokenizer_config.json

Prompt template: ALMA

Translate this from English to Chinese:
English: {prompt}
Chinese:

Example

This example code is obtained from CTranslate2_transformers. More detailed information about the generate_batch methon can be found at CTranslate2_Generator.generate_batch.

import ctranslate2
import transformers

generator = ctranslate2.Generator("avans06/ALMA-13B-ct2-int8_float16")
tokenizer = transformers.AutoTokenizer.from_pretrained("haoranxu/ALMA-13B")

text = "Who is Alan Turing?"
prompt = f"Translate this from English to Chinese:\nEnglish: {text}\nChinese:"
tokens = tokenizer.convert_ids_to_tokens(tokenizer.encode(prompt))

results = generator.generate_batch([tokens], max_length=256, sampling_temperature=0.7, sampling_topp=0.9, repetition_penalty=1.1, include_prompt_in_result=False)

output = tokenizer.decode(results[0].sequences_ids[0])

The following explanations are excerpted from the FAQ section of the author's GitHub README.

What language directions do ALMA support?
Currently, ALMA supports 10 directions: English↔German, Englishs↔Czech, Englishs↔Icelandic, Englishs↔Chinese, Englishs↔Russian. However, it may surprise us in other directions :)

More information

For more information about the original model, see its GitHub repository

Downloads last month: 2