Instructions to use FrontiersMind/Nandi-Mini-150M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FrontiersMind/Nandi-Mini-150M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="FrontiersMind/Nandi-Mini-150M-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FrontiersMind/Nandi-Mini-150M-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FrontiersMind/Nandi-Mini-150M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FrontiersMind/Nandi-Mini-150M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FrontiersMind/Nandi-Mini-150M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FrontiersMind/Nandi-Mini-150M-Instruct

SGLang

How to use FrontiersMind/Nandi-Mini-150M-Instruct 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 "FrontiersMind/Nandi-Mini-150M-Instruct" \
    --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": "FrontiersMind/Nandi-Mini-150M-Instruct",
		"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 "FrontiersMind/Nandi-Mini-150M-Instruct" \
        --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": "FrontiersMind/Nandi-Mini-150M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FrontiersMind/Nandi-Mini-150M-Instruct with Docker Model Runner:
```
docker model run hf.co/FrontiersMind/Nandi-Mini-150M-Instruct
```

vishesh-t27 commited on Apr 13

Commit

7a36923

verified ·

1 Parent(s): 7f282bf

Updated Readme.md

Browse files

Files changed (1) hide show

README.md +0 -10

README.md CHANGED Viewed

@@ -24,7 +24,6 @@ base_model:
 Nandi-Mini-150M-Instruct is a compact, efficient multilingual language model designed for strong performance in resource-constrained environments. It is pre-trained from scratch on 525 billion tokens and further enhanced through instruction tuning and Direct Preference Optimization (DPO). The model supports English and 10 Indic languages.
-We do not employ any benchmaxing tricks; the model is designed to be genuinely strong and highly effective for fine-tuning on downstream tasks.
 Nandi-Mini-150M-Instruct focuses on maximizing performance per parameter through architectural efficiency rather than scale. It is optimized for edge devices, on-prem deployments, and low-latency applications, making it ideal for resource-constrained environments.
 Nandi-Mini-150M-Instruct brings the following key features:
@@ -42,7 +41,6 @@ We’re just getting started with the Nandi series 🚀
 - **Nandi-Mini-500M (Base + Instruct)** — Pre-Training Going On
 - **Nandi-Mini-1B (Base + Instruct)** — Pre-Training Going On
-We are actively working on expanding the Nandi family to cover a wider range of use cases—from lightweight edge deployments to more capable instruction-tuned systems.
 📢 **Blogs & technical deep-dives coming soon**, where we’ll share:
 - Architecture decisions and design trade-offs
@@ -51,14 +49,6 @@ We are actively working on expanding the Nandi family to cover a wider range of
 Stay tuned!
-**This repo contains the instruct Nandi-Mini-150M model**, which has the following features:
-- Type: Causal Language Model
-- Training Stage: Pretraining (from scratch)
-- Architecture: Transformer decoder with RoPE, RMSNorm, SwiGLU, GQA, tied embeddings, **factorize embeddings**
-- Number of Layers: 16*2 [Layer Sharing, effective layer =32]
-- Context Length: 2,048 tokens
-- Vocabulary Size: 131,072
 ## 🌍 Supported Languages

 Nandi-Mini-150M-Instruct is a compact, efficient multilingual language model designed for strong performance in resource-constrained environments. It is pre-trained from scratch on 525 billion tokens and further enhanced through instruction tuning and Direct Preference Optimization (DPO). The model supports English and 10 Indic languages.
 Nandi-Mini-150M-Instruct focuses on maximizing performance per parameter through architectural efficiency rather than scale. It is optimized for edge devices, on-prem deployments, and low-latency applications, making it ideal for resource-constrained environments.
 Nandi-Mini-150M-Instruct brings the following key features:
 - **Nandi-Mini-500M (Base + Instruct)** — Pre-Training Going On
 - **Nandi-Mini-1B (Base + Instruct)** — Pre-Training Going On
 📢 **Blogs & technical deep-dives coming soon**, where we’ll share:
 - Architecture decisions and design trade-offs
 Stay tuned!
 ## 🌍 Supported Languages