Instructions to use BlitherBoom/AutoDroid-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BlitherBoom/AutoDroid-V2 with Transformers:

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

pipe = pipeline("text-generation", model="BlitherBoom/AutoDroid-V2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BlitherBoom/AutoDroid-V2")
model = AutoModelForCausalLM.from_pretrained("BlitherBoom/AutoDroid-V2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BlitherBoom/AutoDroid-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BlitherBoom/AutoDroid-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BlitherBoom/AutoDroid-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BlitherBoom/AutoDroid-V2

SGLang

How to use BlitherBoom/AutoDroid-V2 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 "BlitherBoom/AutoDroid-V2" \
    --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": "BlitherBoom/AutoDroid-V2",
		"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 "BlitherBoom/AutoDroid-V2" \
        --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": "BlitherBoom/AutoDroid-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BlitherBoom/AutoDroid-V2 with Docker Model Runner:
```
docker model run hf.co/BlitherBoom/AutoDroid-V2
```

Fucheng Jia commited on Mar 20, 2025

Commit

8ccfe51

1 Parent(s): f512f39

rm README.md

Browse files

Files changed (2) hide show

README.md +0 -61
config.json +1 -1

README.md DELETED Viewed

@@ -1,61 +0,0 @@
----
-library_name: transformers
-license: other
-base_model: /data/AIR_HF_CACHE/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/8c22764a7e3675c50d4c7c9a4edb474456022b16
-tags:
-- llama-factory
-- full
-- generated_from_trainer
-model-index:
-- name: droidv2_data_verified_merge_no_data_aug_v2_epoch1_llama3.1-8b
-  results: []
----
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-# droidv2_data_verified_merge_no_data_aug_v2_epoch1_llama3.1-8b
-This model is a fine-tuned version of [/data/AIR_HF_CACHE/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/8c22764a7e3675c50d4c7c9a4edb474456022b16](https://huggingface.co//data/AIR_HF_CACHE/hub/models--meta-llama--Meta-Llama-3.1-8B-Instruct/snapshots/8c22764a7e3675c50d4c7c9a4edb474456022b16) on the autodroid dataset.
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
-## Training procedure
-### Training hyperparameters
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 4
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 32
-- total_eval_batch_size: 4
-- optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.01
-- num_epochs: 1.0
-### Training results
-### Framework versions
-- Transformers 4.46.1
-- Pytorch 2.4.0+cu118
-- Datasets 3.0.0
-- Tokenizers 0.20.3

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],

 {
+  "_name_or_path": "AutoDroid-V2",
   "architectures": [
     "LlamaForCausalLM"
   ],