Instructions to use webbigdata/ALMA-7B-Ja-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use webbigdata/ALMA-7B-Ja-V2 with Transformers:

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

pipe = pipeline("text-generation", model="webbigdata/ALMA-7B-Ja-V2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("webbigdata/ALMA-7B-Ja-V2")
model = AutoModelForCausalLM.from_pretrained("webbigdata/ALMA-7B-Ja-V2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use webbigdata/ALMA-7B-Ja-V2 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-V2"
# 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-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/webbigdata/ALMA-7B-Ja-V2

SGLang

How to use webbigdata/ALMA-7B-Ja-V2 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-V2" \
    --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-V2",
		"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-V2" \
        --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-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use webbigdata/ALMA-7B-Ja-V2 with Docker Model Runner:
```
docker model run hf.co/webbigdata/ALMA-7B-Ja-V2
```

dahara1 commited on Mar 4, 2024

Commit

b110495

verified ·

1 Parent(s): c249758

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -9,6 +9,12 @@ language:
 - cs
 license: llama2
 ---
 # webbigdata/ALMA-7B-Ja-V2
 ALMA-7B-Ja-V2は日本語から英語、英語から日本語の翻訳が可能な機械翻訳モデルです。

 - cs
 license: llama2
 ---
+# New Translation model released.
+[C3TR-Adapter](https://huggingface.co/webbigdata/C3TR-Adapter) is the QLoRA adapter for google/gemma-7b.
+Despite the 4-bit quantization, the memory GPU requirement has increased to 8.1 GB.
+However, it is possible to run it with the free version of Colab and the performance is much improved!
 # webbigdata/ALMA-7B-Ja-V2
 ALMA-7B-Ja-V2は日本語から英語、英語から日本語の翻訳が可能な機械翻訳モデルです。