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

Libraries

How to use lyfesan/ViT_BioMedBert_ImageCaptioning_RadGenome with Transformers:

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

pipe = pipeline("image-text-to-text", model="lyfesan/ViT_BioMedBert_ImageCaptioning_RadGenome")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("lyfesan/ViT_BioMedBert_ImageCaptioning_RadGenome")
model = AutoModelForImageTextToText.from_pretrained("lyfesan/ViT_BioMedBert_ImageCaptioning_RadGenome")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lyfesan/ViT_BioMedBert_ImageCaptioning_RadGenome with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/lyfesan/ViT_BioMedBert_ImageCaptioning_RadGenome

SGLang

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

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

lyfesan commited on Jul 28, 2025

Commit

4296dcc

verified ·

1 Parent(s): db53dd4

Upload model

Browse files

Files changed (2) hide show

config.json +2 -2
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -81,7 +81,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 30522
   },
   "decoder_start_token_id": 2,
   "early_stopping": true,
@@ -176,5 +176,5 @@
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.44.0",
-  "vocab_size": 30522
 }

     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
+    "vocab_size": 28895
   },
   "decoder_start_token_id": 2,
   "early_stopping": true,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.44.0",
+  "vocab_size": 28895
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c37b5cf87748f92526c53e776f205514d18f573d20c3754108755595f81833e9
-size 897147000

 version https://git-lfs.github.com/spec/v1
+oid sha256:d54bdabc4fbf5c0c5c40f597092034c70f4beedd5bb7655452b4f6db76da4209
+size 892142332