Instructions to use TIGER-Lab/Mantis-llava-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TIGER-Lab/Mantis-llava-7b with Transformers:

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

pipe = pipeline("image-text-to-text", model="TIGER-Lab/Mantis-llava-7b")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("TIGER-Lab/Mantis-llava-7b")
model = AutoModelForImageTextToText.from_pretrained("TIGER-Lab/Mantis-llava-7b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TIGER-Lab/Mantis-llava-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TIGER-Lab/Mantis-llava-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TIGER-Lab/Mantis-llava-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TIGER-Lab/Mantis-llava-7b

SGLang

How to use TIGER-Lab/Mantis-llava-7b 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 "TIGER-Lab/Mantis-llava-7b" \
    --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": "TIGER-Lab/Mantis-llava-7b",
		"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 "TIGER-Lab/Mantis-llava-7b" \
        --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": "TIGER-Lab/Mantis-llava-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TIGER-Lab/Mantis-llava-7b with Docker Model Runner:
```
docker model run hf.co/TIGER-Lab/Mantis-llava-7b
```

DongfuJiang commited on Apr 13, 2024

Commit

0ddead0

verified ·

1 Parent(s): 41eb026

Update Processor

Browse files

Files changed (5) hide show

README.md +1 -1
added_tokens.json +4 -0
preprocessor_config.json +1 -1
tokenizer.model +3 -0
tokenizer_config.json +1 -1

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
-base_model: llava-hf/llava-1.5-7b-hf
 tags:
 - generated_from_trainer
 model-index:
 - name: llava_1.5_7b_v2_4096
   results: []

 ---
 tags:
 - generated_from_trainer
+base_model: llava-hf/llava-1.5-7b-hf
 model-index:
 - name: llava_1.5_7b_v2_4096
   results: []

added_tokens.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

preprocessor_config.json CHANGED Viewed

@@ -36,7 +36,7 @@
     0.26130258,
     0.27577711
   ],
-  "processor_class": "MLlavaProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {

     0.26130258,
     0.27577711
   ],
+  "processor_class": "LlavaProcessor",
   "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json CHANGED Viewed

@@ -50,7 +50,7 @@
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "padding_side": "left",
-  "processor_class": "MLlavaProcessor",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "trust_remote_code": false,

   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "padding_side": "left",
+  "processor_class": "LlavaProcessor",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "trust_remote_code": false,