Instructions to use nayeshdaggula/sutradhar-3b-moe-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nayeshdaggula/sutradhar-3b-moe-base with Transformers:

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

pipe = pipeline("text-generation", model="nayeshdaggula/sutradhar-3b-moe-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nayeshdaggula/sutradhar-3b-moe-base")
model = AutoModelForCausalLM.from_pretrained("nayeshdaggula/sutradhar-3b-moe-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nayeshdaggula/sutradhar-3b-moe-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nayeshdaggula/sutradhar-3b-moe-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nayeshdaggula/sutradhar-3b-moe-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nayeshdaggula/sutradhar-3b-moe-base

SGLang

How to use nayeshdaggula/sutradhar-3b-moe-base 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 "nayeshdaggula/sutradhar-3b-moe-base" \
    --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": "nayeshdaggula/sutradhar-3b-moe-base",
		"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 "nayeshdaggula/sutradhar-3b-moe-base" \
        --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": "nayeshdaggula/sutradhar-3b-moe-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nayeshdaggula/sutradhar-3b-moe-base with Docker Model Runner:
```
docker model run hf.co/nayeshdaggula/sutradhar-3b-moe-base
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Sutradhar 3B MoE Base

Sutradhar 3B MoE Base is an experimental Indian AI base model.

Current Main Version

This repository currently contains the sutradhar-3b-moe-base-pretrain-v0.2 checkpoint.

Training Type

Causal language modeling / continued base pretraining.

Focus

English text
Telugu text
Indian business and software vocabulary
Coding and application development vocabulary

Important

This is a base model, not an instruction/chat model.

For chat behavior, train or use a separate instruction-tuned checkpoint.

Downloads last month: 93

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for nayeshdaggula/sutradhar-3b-moe-base

Adapters

2 models

nayeshdaggula
/

sutradhar-3b-moe-base