Instructions to use Dimensity/Dimensity-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Dimensity/Dimensity-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Dimensity/Dimensity-3B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Dimensity/Dimensity-3B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Dimensity/Dimensity-3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Dimensity/Dimensity-3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Dimensity/Dimensity-3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Dimensity/Dimensity-3B
- SGLang
How to use Dimensity/Dimensity-3B 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 "Dimensity/Dimensity-3B" \ --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": "Dimensity/Dimensity-3B", "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 "Dimensity/Dimensity-3B" \ --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": "Dimensity/Dimensity-3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Dimensity/Dimensity-3B with Docker Model Runner:
docker model run hf.co/Dimensity/Dimensity-3B
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,9 +3,7 @@ license: mit
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
tags:
|
| 6 |
-
-
|
| 7 |
-
- lora
|
| 8 |
-
- merge
|
| 9 |
---
|
| 10 |
```Dimensity-3B```
|
| 11 |
|
|
@@ -32,5 +30,4 @@ This prompts the model to take on an assistant role.
|
|
| 32 |
As the model was trained on public conversational data, it may generate responses that contain harmful stereotypes or toxic content. The model should be used with caution in sensitive contexts.
|
| 33 |
|
| 34 |
# Caveats and Recommendations
|
| 35 |
-
This model is designed for open-ended conversation. It may sometimes generate plausible-sounding but incorrect information. Outputs should be validated against external sources.
|
| 36 |
-
|
|
|
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
tags:
|
| 6 |
+
- sft
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
```Dimensity-3B```
|
| 9 |
|
|
|
|
| 30 |
As the model was trained on public conversational data, it may generate responses that contain harmful stereotypes or toxic content. The model should be used with caution in sensitive contexts.
|
| 31 |
|
| 32 |
# Caveats and Recommendations
|
| 33 |
+
This model is designed for open-ended conversation. It may sometimes generate plausible-sounding but incorrect information. Outputs should be validated against external sources.
|
|
|