Instructions to use BAAI/Emu3-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/Emu3-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BAAI/Emu3-Chat", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("BAAI/Emu3-Chat", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BAAI/Emu3-Chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BAAI/Emu3-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/Emu3-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BAAI/Emu3-Chat
- SGLang
How to use BAAI/Emu3-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/Emu3-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/Emu3-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/Emu3-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/Emu3-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BAAI/Emu3-Chat with Docker Model Runner:
docker model run hf.co/BAAI/Emu3-Chat
fix for 'DynamicCache' object has no attribute 'get_max_length'
#2
by Howuhh - opened
- modeling_emu3.py +1 -1
modeling_emu3.py
CHANGED
|
@@ -1284,7 +1284,7 @@ class Emu3ForCausalLM(Emu3PreTrainedModel):
|
|
| 1284 |
if isinstance(past_key_values, Cache):
|
| 1285 |
cache_length = past_key_values.get_seq_length()
|
| 1286 |
past_length = past_key_values.seen_tokens
|
| 1287 |
-
max_cache_length = past_key_values.
|
| 1288 |
else:
|
| 1289 |
cache_length = past_length = past_key_values[0][0].shape[2]
|
| 1290 |
max_cache_length = None
|
|
|
|
| 1284 |
if isinstance(past_key_values, Cache):
|
| 1285 |
cache_length = past_key_values.get_seq_length()
|
| 1286 |
past_length = past_key_values.seen_tokens
|
| 1287 |
+
max_cache_length = past_key_values.get_max_cache_shape()
|
| 1288 |
else:
|
| 1289 |
cache_length = past_length = past_key_values[0][0].shape[2]
|
| 1290 |
max_cache_length = None
|