Instructions to use podstack/Shaktimaan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use podstack/Shaktimaan with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("podstack/Shaktimaan")
model = AutoModelForCausalLM.from_pretrained("podstack/Shaktimaan", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use podstack/Shaktimaan with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/podstack/Shaktimaan

SGLang

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

Docker Model Runner
How to use podstack/Shaktimaan with Docker Model Runner:
```
docker model run hf.co/podstack/Shaktimaan
```

podstack commited on 3 days ago

Commit

855fc64

verified ·

1 Parent(s): c1f5d12

Shaktimaan v1.0

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -32,7 +32,7 @@ on [podstack/Shaktimaan-routing](https://huggingface.co/datasets/podstack/Shakti
 - Learns capability routing from data: charts -> the only vision agent, very long inputs -> the long-context agents.
 - **Does not beat hand-written capability rules overall**: Capability rules -> `glm-5.3-flash` reaches
   85.7% at 0.13x. See *Results* and *Findings*.
-- 100% of outputs are valid route JSON (100.0% on the test set).
 ## Output format
 ```json
@@ -40,7 +40,7 @@ on [podstack/Shaktimaan-routing](https://huggingface.co/datasets/podstack/Shakti
 ```
 ## Agent pool
-| agent | model | context | image input | relative cost / token |
 |---|---|---|---|---|
 | `gemma-3-1b` | `google/gemma-3-1b-it` | 32k | no | 0.02 |
 | `kimi-vl` | `Kimi-VL-A3B-Thinking` | 8k | yes | 0.05 |
@@ -57,7 +57,7 @@ to compute routing cost (roughly relative serving cost), not a vendor price.
 import json
 from huggingface_hub import hf_hub_download
 from transformers import AutoModelForCausalLM, AutoTokenizer
-import importlib.util, sys
 repo = "podstack/Shaktimaan"
 spec = importlib.util.spec_from_file_location("common", hf_hub_download(repo, "common.py"))

 - Learns capability routing from data: charts -> the only vision agent, very long inputs -> the long-context agents.
 - **Does not beat hand-written capability rules overall**: Capability rules -> `glm-5.3-flash` reaches
   85.7% at 0.13x. See *Results* and *Findings*.
+- 100.0% of outputs on the test set are valid route JSON.
 ## Output format
 ```json
 ```
 ## Agent pool
+| agent | model | context | image input (in this pool) | relative cost / token |
 |---|---|---|---|---|
 | `gemma-3-1b` | `google/gemma-3-1b-it` | 32k | no | 0.02 |
 | `kimi-vl` | `Kimi-VL-A3B-Thinking` | 8k | yes | 0.05 |
 import json
 from huggingface_hub import hf_hub_download
 from transformers import AutoModelForCausalLM, AutoTokenizer
+import importlib.util
 repo = "podstack/Shaktimaan"
 spec = importlib.util.spec_from_file_location("common", hf_hub_download(repo, "common.py"))