Instructions to use FreedomIntelligence/ALLaVA-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/ALLaVA-3B with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/ALLaVA-3B", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/ALLaVA-3B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FreedomIntelligence/ALLaVA-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/ALLaVA-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/ALLaVA-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/ALLaVA-3B

SGLang

How to use FreedomIntelligence/ALLaVA-3B 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 "FreedomIntelligence/ALLaVA-3B" \
    --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": "FreedomIntelligence/ALLaVA-3B",
		"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 "FreedomIntelligence/ALLaVA-3B" \
        --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": "FreedomIntelligence/ALLaVA-3B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/ALLaVA-3B with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/ALLaVA-3B
```

g-h-chen commited on Feb 29, 2024

Commit

31438a3

verified ·

1 Parent(s): 1b2b1ff

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -1

README.md CHANGED Viewed

@@ -29,6 +29,9 @@ gen_kwargs = {
     'eos_token_id': tokenizer.eos_token_id # this is a must since transformers ~4.37
 }
 response, history = model.chat(
     texts='What is in the image?',
     images=['https://cdn-icons-png.flaticon.com/256/6028/6028690.png'],
@@ -36,14 +39,19 @@ response, history = model.chat(
     **gen_kwargs
 )
 print(response)
 # response:
 # The image contains a large, stylized "HI!" in a bright pink color with yellow outlines. The "HI!" is placed within a speech bubble shape.
 # history:
 # [['What is in the image?', 'The image contains a large, stylized "HI!" in a bright pink color with yellow outlines. The "HI!" is placed within a speech bubble shape.']]
 response, history = model.chat(
     texts='Are you sure?',
     images=['https://cdn-icons-png.flaticon.com/256/6028/6028690.png'], # images need to be passed again in multi-round conversations
@@ -52,7 +60,10 @@ response, history = model.chat(
     **gen_kwargs
 )
 print(response)
 # response:
 # Yes, I'm certain. The image is a graphic representation of the word "HI!" in a speech bubble.

     'eos_token_id': tokenizer.eos_token_id # this is a must since transformers ~4.37
 }
+#################################################################################
+# first round
+#################################################################################
 response, history = model.chat(
     texts='What is in the image?',
     images=['https://cdn-icons-png.flaticon.com/256/6028/6028690.png'],
     **gen_kwargs
 )
+print('response:')
 print(response)
+print('history:')
+print(history)
 # response:
 # The image contains a large, stylized "HI!" in a bright pink color with yellow outlines. The "HI!" is placed within a speech bubble shape.
 # history:
 # [['What is in the image?', 'The image contains a large, stylized "HI!" in a bright pink color with yellow outlines. The "HI!" is placed within a speech bubble shape.']]
+#################################################################################
+# second round
+#################################################################################
 response, history = model.chat(
     texts='Are you sure?',
     images=['https://cdn-icons-png.flaticon.com/256/6028/6028690.png'], # images need to be passed again in multi-round conversations
     **gen_kwargs
 )
+print('response:')
 print(response)
+print('history:')
+print(history)
 # response:
 # Yes, I'm certain. The image is a graphic representation of the word "HI!" in a speech bubble.