Instructions to use aixsatoshi/Honyaku-7b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aixsatoshi/Honyaku-7b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="aixsatoshi/Honyaku-7b-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aixsatoshi/Honyaku-7b-v2")
model = AutoModelForCausalLM.from_pretrained("aixsatoshi/Honyaku-7b-v2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aixsatoshi/Honyaku-7b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aixsatoshi/Honyaku-7b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aixsatoshi/Honyaku-7b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aixsatoshi/Honyaku-7b-v2

SGLang

How to use aixsatoshi/Honyaku-7b-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 "aixsatoshi/Honyaku-7b-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aixsatoshi/Honyaku-7b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "aixsatoshi/Honyaku-7b-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aixsatoshi/Honyaku-7b-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aixsatoshi/Honyaku-7b-v2 with Docker Model Runner:
```
docker model run hf.co/aixsatoshi/Honyaku-7b-v2
```

aixsatoshi commited on Apr 8, 2024

Commit

764ca7f

verified ·

1 Parent(s): 311cc5a

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -9,7 +9,7 @@ Honyaku-7b-v2 is an improved version of its predecessor. This model exhibits enh
 * Improved Multilingual Generation Accuracy: The model has increased precision in following multilingual generation tags.
 * Quality-Reflective Translation: The translation quality of Honyaku-7b is strongly influenced by the pre-training of the base model. Consequently, the quality of translation varies in proportion to the training volume of the original language model.
-* The primary purpose is to translate several hundreds to several thousand tokens. Due to the characteristics of the Base model, translation into Japanese is the most stable.
 * It has been fine-tuned up to 8k tokens, but based on the Base model's characteristics, it supports up to 4k tokens including the prompt.
 **Cautions:**
@@ -26,7 +26,8 @@ Honyaku-7b-v2は、前バージョンの改良版です。このモデルは、
 * 多言語生成の精度向上： モデルは、多言語生成タグに対する追従の精度が向上しました。
 * 翻訳品質の反映： Honyaku-7bの翻訳品質は、ベースモデルの事前学習に強く影響されます。翻訳品質は、元の言語モデルの学習量に比例して変わります。
-* 数100～数1000 tokenの翻訳を主目的としています。Base modelの特徴から、日本語への翻訳が最も安定しています。
 * 8k tokenまでファインチューニングしていますが、Base modelの特徴からprompt含めて4k tokenにまで対応とします。
 **注意点：**

 * Improved Multilingual Generation Accuracy: The model has increased precision in following multilingual generation tags.
 * Quality-Reflective Translation: The translation quality of Honyaku-7b is strongly influenced by the pre-training of the base model. Consequently, the quality of translation varies in proportion to the training volume of the original language model.
+* The primary purpose is to translate about 500 to several thousand tokens. Due to the characteristics of the Base model, translation into Japanese is the most stable.
 * It has been fine-tuned up to 8k tokens, but based on the Base model's characteristics, it supports up to 4k tokens including the prompt.
 **Cautions:**
 * 多言語生成の精度向上： モデルは、多言語生成タグに対する追従の精度が向上しました。
 * 翻訳品質の反映： Honyaku-7bの翻訳品質は、ベースモデルの事前学習に強く影響されます。翻訳品質は、元の言語モデルの学習量に比例して変わります。
+* 500～数1000 tokenの翻訳を主目的としています。短すぎる文、長すぎる文で性能低下。
+* Base modelの特徴から、日本語への翻訳が最も安定しています。
 * 8k tokenまでファインチューニングしていますが、Base modelの特徴からprompt含めて4k tokenにまで対応とします。
 **注意点：**