Instructions to use PocketBrains233/PocketPlanning-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PocketBrains233/PocketPlanning-1 with Transformers:

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

pipe = pipeline("text-generation", model="PocketBrains233/PocketPlanning-1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("PocketBrains233/PocketPlanning-1")
model = AutoModelForMultimodalLM.from_pretrained("PocketBrains233/PocketPlanning-1", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
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 Settings

vLLM

How to use PocketBrains233/PocketPlanning-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PocketBrains233/PocketPlanning-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PocketBrains233/PocketPlanning-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PocketBrains233/PocketPlanning-1

SGLang

How to use PocketBrains233/PocketPlanning-1 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 "PocketBrains233/PocketPlanning-1" \
    --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": "PocketBrains233/PocketPlanning-1",
		"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 "PocketBrains233/PocketPlanning-1" \
        --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": "PocketBrains233/PocketPlanning-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PocketBrains233/PocketPlanning-1 with Docker Model Runner:
```
docker model run hf.co/PocketBrains233/PocketPlanning-1
```

PocketBrains233 commited on Mar 25

Commit

5f4f403

verified ·

1 Parent(s): 7ed6c6d

Update README: rename to PocketPlaning-1

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -17,9 +17,9 @@ library_name: transformers
 pipeline_tag: text-generation
 ---
-# PocketPlan-27B
-**PocketPlan-27B** is a specialized AI agent planning model built on Qwen3.5-27B. It is fine-tuned for intelligent task routing, complexity estimation, and tool-calling orchestration in agentic workflows.
 ## Key Capabilities
@@ -46,7 +46,7 @@ pipeline_tag: text-generation
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model_name = "PocketBrains/PocketPlan-27B"
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
@@ -65,7 +65,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ### With vLLM
 ```bash
-vllm serve PocketBrains/PocketPlan-27B \
     --tensor-parallel-size 2 \
     --max-model-len 131072 \
     --dtype bfloat16 \
@@ -76,7 +76,7 @@ vllm serve PocketBrains/PocketPlan-27B \
 ## Intended Use
-PocketPlan-27B is designed to serve as the planning and routing layer inside AI agent systems. It determines *what to do next* and *how much compute to spend doing it*, enabling cost-efficient agent execution by routing simple tasks locally and escalating complex tasks to frontier models.
 ## Limitations
@@ -88,10 +88,10 @@ PocketPlan-27B is designed to serve as the planning and routing layer inside AI
 ```bibtex
 @misc{pocketplan2026,
-  title={PocketPlan-27B: Efficient Planning Models for AI Agents},
   author={PocketBrains Inc.},
   year={2026},
-  url={https://huggingface.co/PocketBrains/PocketPlan-27B}
 }
 ```

 pipeline_tag: text-generation
 ---
+# PocketPlaning-1
+**PocketPlaning-1** is a specialized AI agent planning model built on Qwen3.5-27B. It is fine-tuned for intelligent task routing, complexity estimation, and tool-calling orchestration in agentic workflows.
 ## Key Capabilities
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model_name = "PocketBrains/PocketPlaning-1"
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
 ### With vLLM
 ```bash
+vllm serve PocketBrains/PocketPlaning-1 \
     --tensor-parallel-size 2 \
     --max-model-len 131072 \
     --dtype bfloat16 \
 ## Intended Use
+PocketPlaning-1 is designed to serve as the planning and routing layer inside AI agent systems. It determines *what to do next* and *how much compute to spend doing it*, enabling cost-efficient agent execution by routing simple tasks locally and escalating complex tasks to frontier models.
 ## Limitations
 ```bibtex
 @misc{pocketplan2026,
+  title={PocketPlaning-1: Efficient Planning Models for AI Agents},
   author={PocketBrains Inc.},
   year={2026},
+  url={https://huggingface.co/PocketBrains/PocketPlaning-1}
 }
 ```