Instructions to use stabilityai/japanese-stablelm-3b-4e1t-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stabilityai/japanese-stablelm-3b-4e1t-base with Transformers:

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

pipe = pipeline("text-generation", model="stabilityai/japanese-stablelm-3b-4e1t-base", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("stabilityai/japanese-stablelm-3b-4e1t-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stabilityai/japanese-stablelm-3b-4e1t-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stabilityai/japanese-stablelm-3b-4e1t-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stabilityai/japanese-stablelm-3b-4e1t-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stabilityai/japanese-stablelm-3b-4e1t-base

SGLang

How to use stabilityai/japanese-stablelm-3b-4e1t-base 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 "stabilityai/japanese-stablelm-3b-4e1t-base" \
    --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": "stabilityai/japanese-stablelm-3b-4e1t-base",
		"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 "stabilityai/japanese-stablelm-3b-4e1t-base" \
        --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": "stabilityai/japanese-stablelm-3b-4e1t-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stabilityai/japanese-stablelm-3b-4e1t-base with Docker Model Runner:
```
docker model run hf.co/stabilityai/japanese-stablelm-3b-4e1t-base
```

iwiwi commited on Oct 16, 2023

Commit

35a3f4a

1 Parent(s): 5ba0240

Update README.md

Browse files

Files changed (1) hide show

README.md +22 -0

README.md CHANGED Viewed

@@ -30,6 +30,28 @@ TODO
 * **License**: This model is licensed under [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0).
 * **Contact**: For questions and comments about the model, please email `lm@stability.ai`
 ## Use and Limitations

 * **License**: This model is licensed under [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0).
 * **Contact**: For questions and comments about the model, please email `lm@stability.ai`
+### Model Architecture
+The model is a decoder-only transformer similar to the LLaMA ([Touvron et al., 2023](https://arxiv.org/abs/2307.09288)) architecture with the following modifications:
+| Parameters     | Hidden Size | Layers | Heads | Sequence Length |
+|----------------|-------------|--------|-------|-----------------|
+| 2,795,443,200  | 2560        | 32     | 32    | 4096            |
+* **Position Embeddings**: Rotary Position Embeddings ([Su et al., 2021](https://arxiv.org/abs/2104.09864)) applied to the first 25% of head embedding dimensions for improved throughput following [Black et al. (2022)](https://arxiv.org/pdf/2204.06745.pdf).
+* **Normalization**: LayerNorm ([Ba et al., 2016](https://arxiv.org/abs/1607.06450)) with learned bias terms as opposed to RMSNorm ([Zhang & Sennrich, 2019](https://arxiv.org/abs/1910.07467)).
+* **Tokenizer**: GPT-NeoX ([Black et al., 2022](https://arxiv.org/abs/2204.06745)).
+### Training Dataset
+Around 100B tokens from a mixture of the following corpora were used for the continued pretraining.
+- [Japanese/English Wikipedia](https://dumps.wikimedia.org/other/cirrussearch)
+- [Japanese mc4](https://huggingface.co/datasets/mc4)
+- [Japanese CC-100](http://data.statmt.org/cc-100/ja.txt.xz)
+- [Japanese OSCAR](https://oscar-project.github.io/documentation/)
+- [SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B)
 ## Use and Limitations