Instructions to use HuggingFaceM4/VLM_WebSight_finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceM4/VLM_WebSight_finetuned with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="HuggingFaceM4/VLM_WebSight_finetuned", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("HuggingFaceM4/VLM_WebSight_finetuned", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceM4/VLM_WebSight_finetuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/VLM_WebSight_finetuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceM4/VLM_WebSight_finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceM4/VLM_WebSight_finetuned

SGLang

How to use HuggingFaceM4/VLM_WebSight_finetuned 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 "HuggingFaceM4/VLM_WebSight_finetuned" \
    --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": "HuggingFaceM4/VLM_WebSight_finetuned",
		"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 "HuggingFaceM4/VLM_WebSight_finetuned" \
        --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": "HuggingFaceM4/VLM_WebSight_finetuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceM4/VLM_WebSight_finetuned with Docker Model Runner:
```
docker model run hf.co/HuggingFaceM4/VLM_WebSight_finetuned
```

VictorSanh commited on Jan 9, 2024

Commit

0bfa212

1 Parent(s): 719f253

fix

Browse files

Files changed (1) hide show

vision.py +7 -7

vision.py CHANGED Viewed

@@ -192,7 +192,7 @@ class SiglipVisionModelOutput(ModelOutput):
 class SiglipVisionEmbeddings(nn.Module):
-    def __init__(self, config: VMistralVisionConfig):
         super().__init__()
         self.config = config
         self.embed_dim = config.hidden_size
@@ -565,7 +565,7 @@ class SiglipMLP(nn.Module):
 # Copied from transformers.models.clip.modeling_clip.CLIPEncoderLayer with CLIP->Siglip
 class SiglipEncoderLayer(nn.Module):
-    def __init__(self, config: VMistralVisionConfig):
         super().__init__()
         self.embed_dim = config.hidden_size
         self.self_attn = (
@@ -1001,7 +1001,7 @@ class SiglipEncoder(nn.Module):
 class SiglipVisionTransformer(nn.Module):
-    def __init__(self, config: VMistralVisionConfig):
         super().__init__()
         self.config = config
         embed_dim = config.hidden_size
@@ -1012,7 +1012,7 @@ class SiglipVisionTransformer(nn.Module):
         self.head = SiglipMultiheadAttentionPoolingHead(config)
     # @add_start_docstrings_to_model_forward(SIGLIP_VISION_INPUTS_DOCSTRING)
-    # @replace_return_docstrings(output_type=BaseModelOutputWithPooling, config_class=VMistralVisionConfig)
     def forward(
         self,
         pixel_values,
@@ -1058,7 +1058,7 @@ class SiglipVisionTransformer(nn.Module):
 class SiglipMultiheadAttentionPoolingHead(nn.Module):
     """Multihead Attention Pooling."""
-    def __init__(self, config: VMistralVisionConfig):
         super().__init__()
         self.probe = nn.Parameter(torch.randn(1, 1, config.hidden_size))
@@ -1084,7 +1084,7 @@ class SiglipMultiheadAttentionPoolingHead(nn.Module):
 #     SIGLIP_START_DOCSTRING,
 # )
 class SiglipVisionModel(nn.Module):
-    def __init__(self, config: VMistralVisionConfig):
         super().__init__()
         self.vision_model = SiglipVisionTransformer(config)
@@ -1096,7 +1096,7 @@ class SiglipVisionModel(nn.Module):
     #     return self.vision_model.embeddings.patch_embedding
     # @add_start_docstrings_to_model_forward(SIGLIP_VISION_INPUTS_DOCSTRING)
-    # @replace_return_docstrings(output_type=BaseModelOutputWithPooling, config_class=VMistralVisionConfig)
     def forward(
         self,
         pixel_values,

 class SiglipVisionEmbeddings(nn.Module):
+    def __init__(self, config: Img2HTMLVisionConfig):
         super().__init__()
         self.config = config
         self.embed_dim = config.hidden_size
 # Copied from transformers.models.clip.modeling_clip.CLIPEncoderLayer with CLIP->Siglip
 class SiglipEncoderLayer(nn.Module):
+    def __init__(self, config: Img2HTMLVisionConfig):
         super().__init__()
         self.embed_dim = config.hidden_size
         self.self_attn = (
 class SiglipVisionTransformer(nn.Module):
+    def __init__(self, config: Img2HTMLVisionConfig):
         super().__init__()
         self.config = config
         embed_dim = config.hidden_size
         self.head = SiglipMultiheadAttentionPoolingHead(config)
     # @add_start_docstrings_to_model_forward(SIGLIP_VISION_INPUTS_DOCSTRING)
+    # @replace_return_docstrings(output_type=BaseModelOutputWithPooling, config_class=Img2HTMLVisionConfig)
     def forward(
         self,
         pixel_values,
 class SiglipMultiheadAttentionPoolingHead(nn.Module):
     """Multihead Attention Pooling."""
+    def __init__(self, config: Img2HTMLVisionConfig):
         super().__init__()
         self.probe = nn.Parameter(torch.randn(1, 1, config.hidden_size))
 #     SIGLIP_START_DOCSTRING,
 # )
 class SiglipVisionModel(nn.Module):
+    def __init__(self, config: Img2HTMLVisionConfig):
         super().__init__()
         self.vision_model = SiglipVisionTransformer(config)
     #     return self.vision_model.embeddings.patch_embedding
     # @add_start_docstrings_to_model_forward(SIGLIP_VISION_INPUTS_DOCSTRING)
+    # @replace_return_docstrings(output_type=BaseModelOutputWithPooling, config_class=Img2HTMLVisionConfig)
     def forward(
         self,
         pixel_values,