Instructions to use echo840/Monkey-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use echo840/Monkey-Chat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="echo840/Monkey-Chat", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("echo840/Monkey-Chat", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use echo840/Monkey-Chat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "echo840/Monkey-Chat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "echo840/Monkey-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/echo840/Monkey-Chat
- SGLang
How to use echo840/Monkey-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 "echo840/Monkey-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": "echo840/Monkey-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 "echo840/Monkey-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": "echo840/Monkey-Chat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use echo840/Monkey-Chat with Docker Model Runner:
docker model run hf.co/echo840/Monkey-Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -119,7 +119,9 @@ tokenizer.padding_side = 'left'
|
|
| 119 |
tokenizer.pad_token_id = tokenizer.eod_id
|
| 120 |
img_path = ""
|
| 121 |
question = ""
|
| 122 |
-
|
|
|
|
|
|
|
| 123 |
|
| 124 |
input_ids = tokenizer(query, return_tensors='pt', padding='longest')
|
| 125 |
attention_mask = input_ids.attention_mask
|
|
|
|
| 119 |
tokenizer.pad_token_id = tokenizer.eod_id
|
| 120 |
img_path = ""
|
| 121 |
question = ""
|
| 122 |
+
|
| 123 |
+
#Monkey-Chat has the same prompt format for both vqa and detailed caption.
|
| 124 |
+
query = f'<img>{img_path}</img> {question} Answer: '
|
| 125 |
|
| 126 |
input_ids = tokenizer(query, return_tensors='pt', padding='longest')
|
| 127 |
attention_mask = input_ids.attention_mask
|