Instructions to use nyanko7/llava-v1.6-34b-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nyanko7/llava-v1.6-34b-finetune with Transformers:

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

pipe = pipeline("text-generation", model="nyanko7/llava-v1.6-34b-finetune")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("nyanko7/llava-v1.6-34b-finetune")
model = AutoModelForCausalLM.from_pretrained("nyanko7/llava-v1.6-34b-finetune")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nyanko7/llava-v1.6-34b-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nyanko7/llava-v1.6-34b-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nyanko7/llava-v1.6-34b-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nyanko7/llava-v1.6-34b-finetune

SGLang

How to use nyanko7/llava-v1.6-34b-finetune 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 "nyanko7/llava-v1.6-34b-finetune" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nyanko7/llava-v1.6-34b-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "nyanko7/llava-v1.6-34b-finetune" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nyanko7/llava-v1.6-34b-finetune",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nyanko7/llava-v1.6-34b-finetune with Docker Model Runner:
```
docker model run hf.co/nyanko7/llava-v1.6-34b-finetune
```

If is it posssible to release your finetune code?

by xingguangzhou - opened Apr 9, 2024

Discussion

xingguangzhou

Apr 9, 2024

If is it posssible to release your finetune code?
I use the offical llava1.6-34b model to finetune and encounter this error, have you meet this error, how to fix?

WARNING: tokenization mismatch: 1494 vs. 1495. (ignored)
WARNING: tokenization mismatch: 1548 vs. 1549. (ignored)
WARNING: tokenization mismatch: 1528 vs. 1529. (ignored)
WARNING: tokenization mismatch: 1494 vs. 1495. (ignored)
WARNING: tokenization mismatch: 1558 vs. 1559. (ignored)
WARNING: tokenization mismatch: 1465 vs. 1466. (ignored)
WARNING: tokenization mismatch: 1488 vs. 1489. (ignored)
WARNING: tokenization mismatch: 1788 vs. 1789. (ignored)
WARNING: tokenization mismatch: 1823 vs. 1824. (ignored)
WARNING: tokenization mismatch: 1757 vs. 1758. (ignored)
WARNING: tokenization mismatch: 1771 vs. 1772. (ignored)
WARNING: tokenization mismatch: 1755 vs. 1756. (ignored)
WARNING: tokenization mismatch: 1782 vs. 1783. (ignored)
WARNING: tokenization mismatch: 1806 vs. 1807. (ignored)
WARNING: tokenization mismatch: 1766 vs. 1767. (ignored)
WARNING: tokenization mismatch: 1669 vs. 1670. (ignored)
WARNING: tokenization mismatch: 1707 vs. 1708. (ignored)
WARNING: tokenization mismatch: 1754 vs. 1755. (ignored)
WARNING: tokenization mismatch: 1685 vs. 1686. (ignored)
WARNING: tokenization mismatch: 1612 vs. 1613. (ignored)
WARNING: tokenization mismatch: 1673 vs. 1674. (ignored)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment