Instructions to use Adesh696/git-base-flickr8k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Adesh696/git-base-flickr8k with Transformers:

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

pipe = pipeline("image-text-to-text", model="Adesh696/git-base-flickr8k")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("Adesh696/git-base-flickr8k")
model = AutoModelForImageTextToText.from_pretrained("Adesh696/git-base-flickr8k")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Adesh696/git-base-flickr8k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Adesh696/git-base-flickr8k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Adesh696/git-base-flickr8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Adesh696/git-base-flickr8k

SGLang

How to use Adesh696/git-base-flickr8k 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 "Adesh696/git-base-flickr8k" \
    --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": "Adesh696/git-base-flickr8k",
		"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 "Adesh696/git-base-flickr8k" \
        --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": "Adesh696/git-base-flickr8k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Adesh696/git-base-flickr8k with Docker Model Runner:
```
docker model run hf.co/Adesh696/git-base-flickr8k
```

Adesh696 commited on Jan 15, 2024

Commit

52cf996

verified ·

1 Parent(s): aab6222

Create tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +19 -0

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,19 @@

+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "processor_class": "GitProcessor",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}