Instructions to use Stanford-ILIAD/minivla-libero90-prismatic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Stanford-ILIAD/minivla-libero90-prismatic with Transformers:

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

pipe = pipeline("image-text-to-text", model="Stanford-ILIAD/minivla-libero90-prismatic")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Stanford-ILIAD/minivla-libero90-prismatic", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Stanford-ILIAD/minivla-libero90-prismatic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Stanford-ILIAD/minivla-libero90-prismatic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Stanford-ILIAD/minivla-libero90-prismatic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Stanford-ILIAD/minivla-libero90-prismatic

SGLang

How to use Stanford-ILIAD/minivla-libero90-prismatic 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 "Stanford-ILIAD/minivla-libero90-prismatic" \
    --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": "Stanford-ILIAD/minivla-libero90-prismatic",
		"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 "Stanford-ILIAD/minivla-libero90-prismatic" \
        --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": "Stanford-ILIAD/minivla-libero90-prismatic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Stanford-ILIAD/minivla-libero90-prismatic with Docker Model Runner:
```
docker model run hf.co/Stanford-ILIAD/minivla-libero90-prismatic
```

minivla-libero90-prismatic / run-metrics.jsonl

belkhale

Upload folder using huggingface_hub

ec2e79f verified over 1 year ago

Raw

History Blame Contribute Delete

1.37 kB

{"hparams": {"data_root_dir": "/hai/scratch/belkhale/datasets", "hf_token": ".hf_token", "image_aug": false, "is_resume": true, "pretrained_checkpoint": null, "resume_epoch": null, "resume_step": null, "run_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--extra_tokens", "run_id_note": "extra_tokens", "run_root_dir": "runs", "save_interval": 2500, "seed": 7, "trackers": ["jsonl", "wandb"], "vla": {"action_tokenizer": "extra_action_tokenizer", "base_vlm": "runs/prism-qwen25-extra-dinosiglip-224px+0_5b+stage-finetune+x7/", "data_mix": "libero_90", "enable_gradient_checkpointing": true, "enable_mixed_precision_training": true, "epochs": 1000, "expected_world_size": 8, "freeze_llm_backbone": false, "freeze_vision_backbone": false, "global_batch_size": 256, "learning_rate": 2e-05, "lr_scheduler_type": "constant", "max_grad_norm": 1.0, "max_steps": null, "per_device_batch_size": 32, "reduce_in_full_precision": true, "save_every_n_steps": 25000, "shuffle_buffer_size": 256000, "train_strategy": "fsdp-full-shard", "type": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90", "unfreeze_last_llm_layer": false, "vla_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90", "warmup_ratio": 0.0, "weight_decay": 0.0}, "wandb_entity": null, "wandb_project": "prismatic"}, "run_id": "prism-qwen25-dinosiglip-224px+0_5b+mx-libero-90+n1+b32+x7--extra_tokens"}