Instructions to use webbigdata/ALMA-7B-Ja with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use webbigdata/ALMA-7B-Ja with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="webbigdata/ALMA-7B-Ja")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("webbigdata/ALMA-7B-Ja") model = AutoModelForMultimodalLM.from_pretrained("webbigdata/ALMA-7B-Ja") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use webbigdata/ALMA-7B-Ja with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "webbigdata/ALMA-7B-Ja" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "webbigdata/ALMA-7B-Ja", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/webbigdata/ALMA-7B-Ja
- SGLang
How to use webbigdata/ALMA-7B-Ja 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 "webbigdata/ALMA-7B-Ja" \ --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": "webbigdata/ALMA-7B-Ja", "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 "webbigdata/ALMA-7B-Ja" \ --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": "webbigdata/ALMA-7B-Ja", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use webbigdata/ALMA-7B-Ja with Docker Model Runner:
docker model run hf.co/webbigdata/ALMA-7B-Ja
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,13 +13,15 @@ language:
|
|
| 13 |
Original ALMA Model [ALMA-7B](https://huggingface.co/haoranxu/ALMA-7B). (26.95GB)
|
| 14 |
|
| 15 |
ALMA-7B-Ja is a machine translation model that uses ALMA's learning method to translate Japanese to English.(13.3GB)
|
|
|
|
| 16 |
|
| 17 |
-
Like the original model, This model has been verified that it also has a translation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
-
german and english
|
| 20 |
-
Chinese and English
|
| 21 |
-
Icelandic and English
|
| 22 |
-
Czech and English
|
| 23 |
|
| 24 |
Models | de | cs | is | zh | ru/jp | Avg. |
|
| 25 |
|----------------|--------|--------|--------|--------|--------|--------|
|
|
@@ -43,7 +45,6 @@ And translation ability for languages other than Japanese and English has deteri
|
|
| 43 |
[webbigdata/ALMA-7B-Ja-GPTQ-Ja-En](https://huggingface.co/webbigdata/ALMA-7B-Ja-GPTQ-Ja-En)
|
| 44 |
|
| 45 |
|
| 46 |
-
|
| 47 |
**ALMA** (**A**dvanced **L**anguage **M**odel-based tr**A**nslator) 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.
|
| 48 |
Please find more details in their [paper](https://arxiv.org/abs/2309.11674).
|
| 49 |
```
|
|
|
|
| 13 |
Original ALMA Model [ALMA-7B](https://huggingface.co/haoranxu/ALMA-7B). (26.95GB)
|
| 14 |
|
| 15 |
ALMA-7B-Ja is a machine translation model that uses ALMA's learning method to translate Japanese to English.(13.3GB)
|
| 16 |
+
The original ALMA-7B supports English and Russian(ru) translation. This model supports Japanese(ja) and English translations instead of Russian.
|
| 17 |
|
| 18 |
+
Like the original model, This model has been verified that it also has a translation ability between the following languages, but if you want the translation function for these languages, it is better to use the original [ALMA-13B model](https://huggingface.co/haoranxu/ALMA-13B).
|
| 19 |
+
|
| 20 |
+
German(de) and English(en)
|
| 21 |
+
Chinese(zh) and English(en)
|
| 22 |
+
Icelandic(is) and English(en)
|
| 23 |
+
Czech(cs) and English(en)
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
Models | de | cs | is | zh | ru/jp | Avg. |
|
| 27 |
|----------------|--------|--------|--------|--------|--------|--------|
|
|
|
|
| 45 |
[webbigdata/ALMA-7B-Ja-GPTQ-Ja-En](https://huggingface.co/webbigdata/ALMA-7B-Ja-GPTQ-Ja-En)
|
| 46 |
|
| 47 |
|
|
|
|
| 48 |
**ALMA** (**A**dvanced **L**anguage **M**odel-based tr**A**nslator) 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.
|
| 49 |
Please find more details in their [paper](https://arxiv.org/abs/2309.11674).
|
| 50 |
```
|