Instructions to use BAAI/Emu2-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/Emu2-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BAAI/Emu2-Chat", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("BAAI/Emu2-Chat", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BAAI/Emu2-Chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BAAI/Emu2-Chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BAAI/Emu2-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BAAI/Emu2-Chat
- SGLang
How to use BAAI/Emu2-Chat 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 "BAAI/Emu2-Chat" \ --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": "BAAI/Emu2-Chat", "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 "BAAI/Emu2-Chat" \ --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": "BAAI/Emu2-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BAAI/Emu2-Chat with Docker Model Runner:
docker model run hf.co/BAAI/Emu2-Chat
fix a typo
Browse files
README.md
CHANGED
|
@@ -16,7 +16,6 @@ language:
|
|
| 16 |
|
| 17 |
## Inference (Huggingface Version)
|
| 18 |
|
| 19 |
-
### Emu2 & Emu2-Chat
|
| 20 |
#### Single GPU
|
| 21 |
|
| 22 |
```python
|
|
@@ -182,7 +181,7 @@ device_map["model.decoder.lm.lm_head"] = 0
|
|
| 182 |
|
| 183 |
model = load_checkpoint_and_dispatch(
|
| 184 |
model,
|
| 185 |
-
'local/path/to/hf/version/Emu2/model',
|
| 186 |
device_map=device_map).eval()
|
| 187 |
|
| 188 |
# `[<IMG_PLH>]` is the image placeholder which will be replaced by image embeddings.
|
|
|
|
| 16 |
|
| 17 |
## Inference (Huggingface Version)
|
| 18 |
|
|
|
|
| 19 |
#### Single GPU
|
| 20 |
|
| 21 |
```python
|
|
|
|
| 181 |
|
| 182 |
model = load_checkpoint_and_dispatch(
|
| 183 |
model,
|
| 184 |
+
'local/path/to/hf/version/Emu2-Chat/model',
|
| 185 |
device_map=device_map).eval()
|
| 186 |
|
| 187 |
# `[<IMG_PLH>]` is the image placeholder which will be replaced by image embeddings.
|