Instructions to use vikhyatk/moondream1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vikhyatk/moondream1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="vikhyatk/moondream1", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("vikhyatk/moondream1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use vikhyatk/moondream1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "vikhyatk/moondream1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "vikhyatk/moondream1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/vikhyatk/moondream1
- SGLang
How to use vikhyatk/moondream1 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 "vikhyatk/moondream1" \ --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": "vikhyatk/moondream1", "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 "vikhyatk/moondream1" \ --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": "vikhyatk/moondream1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use vikhyatk/moondream1 with Docker Model Runner:
docker model run hf.co/vikhyatk/moondream1
Upload Moondream
Browse files- moondream.py +1 -1
- text_model.py +1 -2
moondream.py
CHANGED
|
@@ -12,7 +12,7 @@ class Moondream(PreTrainedModel):
|
|
| 12 |
def __init__(self, config):
|
| 13 |
super().__init__(config)
|
| 14 |
self.vision_encoder = VisionEncoder()
|
| 15 |
-
self.text_model = TextModel(config
|
| 16 |
|
| 17 |
@property
|
| 18 |
def device(self):
|
|
|
|
| 12 |
def __init__(self, config):
|
| 13 |
super().__init__(config)
|
| 14 |
self.vision_encoder = VisionEncoder()
|
| 15 |
+
self.text_model = TextModel(config)
|
| 16 |
|
| 17 |
@property
|
| 18 |
def device(self):
|
text_model.py
CHANGED
|
@@ -7,7 +7,7 @@ transformers.logging.set_verbosity_error()
|
|
| 7 |
|
| 8 |
|
| 9 |
class TextModel(nn.Module):
|
| 10 |
-
def __init__(self, config
|
| 11 |
super().__init__()
|
| 12 |
|
| 13 |
if type(config.phi_config) == dict:
|
|
@@ -17,4 +17,3 @@ class TextModel(nn.Module):
|
|
| 17 |
|
| 18 |
self.model = PhiForCausalLM(phi_config)
|
| 19 |
self.text_emb = self.model.get_input_embeddings()
|
| 20 |
-
self.tokenizer = tokenizer
|
|
|
|
| 7 |
|
| 8 |
|
| 9 |
class TextModel(nn.Module):
|
| 10 |
+
def __init__(self, config) -> None:
|
| 11 |
super().__init__()
|
| 12 |
|
| 13 |
if type(config.phi_config) == dict:
|
|
|
|
| 17 |
|
| 18 |
self.model = PhiForCausalLM(phi_config)
|
| 19 |
self.text_emb = self.model.get_input_embeddings()
|
|
|