Instructions to use ChayanM/ViT-RadBert_Mimic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChayanM/ViT-RadBert_Mimic with Transformers:

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

pipe = pipeline("image-text-to-text", model="ChayanM/ViT-RadBert_Mimic")

# Load model directly
from transformers import AutoTokenizer, AutoModelForImageTextToText

tokenizer = AutoTokenizer.from_pretrained("ChayanM/ViT-RadBert_Mimic")
model = AutoModelForImageTextToText.from_pretrained("ChayanM/ViT-RadBert_Mimic")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ChayanM/ViT-RadBert_Mimic with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ChayanM/ViT-RadBert_Mimic

SGLang

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

Docker Model Runner
How to use ChayanM/ViT-RadBert_Mimic with Docker Model Runner:
```
docker model run hf.co/ChayanM/ViT-RadBert_Mimic
```

ChayanM commited on Apr 4, 2024

Commit

e717776

verified ·

1 Parent(s): 7c46ce3

Training in progress, epoch 1

Browse files

Files changed (3) hide show

config.json +5 -5
model.safetensors +2 -2
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -85,7 +85,7 @@
   },
   "decoder_start_token_id": 0,
   "encoder": {
-    "_name_or_path": "google/vit-large-patch16-384",
     "add_cross_attention": false,
     "architectures": [
       "ViTForImageClassification"
@@ -109,7 +109,7 @@
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.0,
-    "hidden_size": 1024,
     "id2label": {
       "0": "tench, Tinca tinca",
       "1": "goldfish, Carassius auratus",
@@ -1114,7 +1114,7 @@
     },
     "image_size": 384,
     "initializer_range": 0.02,
-    "intermediate_size": 4096,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
@@ -2124,11 +2124,11 @@
     "min_length": 0,
     "model_type": "vit",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 16,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_channels": 3,
-    "num_hidden_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,

   },
   "decoder_start_token_id": 0,
   "encoder": {
+    "_name_or_path": "google/vit-base-patch16-384",
     "add_cross_attention": false,
     "architectures": [
       "ViTForImageClassification"
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
     "id2label": {
       "0": "tench, Tinca tinca",
       "1": "goldfish, Carassius auratus",
     },
     "image_size": 384,
     "initializer_range": 0.02,
+    "intermediate_size": 3072,
     "is_decoder": false,
     "is_encoder_decoder": false,
     "label2id": {
     "min_length": 0,
     "model_type": "vit",
     "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_channels": 3,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39446144a75ed83b4a159da1cb72154dbe6f663a3f612b2d5e43db6e34ab8300
-size 1834458276

 version https://git-lfs.github.com/spec/v1
+oid sha256:2371b80236ca2f8b5d62586264a192fae13de09de32ff400f45f0cf1e45325d4
+size 959047772

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8f69f2b9078d3ef7f7df637b1b4336f3111b1afb1a0ef3a59f96164d47ad590
 size 4411

 version https://git-lfs.github.com/spec/v1
+oid sha256:1a0f96a1663ea83cf24651aa3e0a3b789a732732fa915133e48bb93d0fa04d8e
 size 4411