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

Libraries

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

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

pipe = pipeline("text-generation", model="FrontiersMind/Nandi-Mini-150M", trust_remote_code=True)

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FrontiersMind/Nandi-Mini-150M 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"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FrontiersMind/Nandi-Mini-150M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use FrontiersMind/Nandi-Mini-150M 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" \
    --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": "FrontiersMind/Nandi-Mini-150M",
		"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 "FrontiersMind/Nandi-Mini-150M" \
        --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": "FrontiersMind/Nandi-Mini-150M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

vishesh-t27 commited on Apr 2

Commit

7bee726

verified ·

1 Parent(s): f5213b6

updated Readme.md

Browse files

Files changed (1) hide show

README.md +7 -6

README.md CHANGED Viewed

@@ -35,9 +35,9 @@ Nandi-Mini-150M brings the following key features:
 We’re just getting started with the Nandi series 🚀
 - **Nandi-Mini-150M (Base)** — *Available now*
-- **Nandi-Mini-150M (Instruct)** — Coming soon (open-sourced)
-- **Nandi-Mini-500M (Base + Instruct)** — Planned next
-- **Nandi-Mini-1B (Base + Instruct)** — Final milestone in the current roadmap
 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.
@@ -65,7 +65,7 @@ The model is trained on English and a diverse set of Indic languages, including:
 ## Benchmark Results
-## 📊 Benchmark Comparison (Nandi-150M Focus)
 | Model Name         | Parameters | Tokens(B) | HellaSwag | Winogrande | GPQA  | MMLU | GSM8K | HumanEval | Average |
 |------------------|---------------|------------------|----------|------------|------|------|-------|-----------|---------|
@@ -75,7 +75,7 @@ The model is trained on English and a diverse set of Indic languages, including:
 | **Nandi-Mini-150M-Base** | **150**     | **500**          | 37.20    | 52.32      | **28.57** | **28.86** | **2.58** | **4.27** | **25.63** |
-## 📊 Model Benchmark Comparison With Bigger Models (350M–600M Class)
 | Model Name            | Parameters | Tokens(B) | HellaSwag | Winogrande | GPQA  | MMLU | GSM8K | HumanEval | Average |
 |---------------------|---------------|------------------|----------|------------|------|------|-------|-----------|---------|
@@ -87,7 +87,8 @@ The model is trained on English and a diverse set of Indic languages, including:
 | SmolLM2-360M-Base   | 360           | 40000            | 56.30    | 59.19      | 25.22| 25.55| 2.88  | 0.00      | 28.19   |
 | **Nandi-Mini-150M-Base** | **150**       | 500          | 37.20| 52.32  | 28.57 | 28.86 | 2.58 | 4.27 | 25.63 |
 ## 🚀 Usage

 We’re just getting started with the Nandi series 🚀
 - **Nandi-Mini-150M (Base)** — *Available now*
+- **Nandi-Mini-150M (Instruct)** — Open Sourcing Next week
+- **Nandi-Mini-500M (Base + Instruct)** — Training Going On
+- **Nandi-Mini-1B (Base + Instruct)** — 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.
 ## Benchmark Results
+## 📊 Benchmark Comparison (~150M Class)
 | Model Name         | Parameters | Tokens(B) | HellaSwag | Winogrande | GPQA  | MMLU | GSM8K | HumanEval | Average |
 |------------------|---------------|------------------|----------|------------|------|------|-------|-----------|---------|
 | **Nandi-Mini-150M-Base** | **150**     | **500**          | 37.20    | 52.32      | **28.57** | **28.86** | **2.58** | **4.27** | **25.63** |
+## 📊 Model Benchmark Comparison With Slightly Bigger Models (350M–600M Class)
 | Model Name            | Parameters | Tokens(B) | HellaSwag | Winogrande | GPQA  | MMLU | GSM8K | HumanEval | Average |
 |---------------------|---------------|------------------|----------|------------|------|------|-------|-----------|---------|
 | SmolLM2-360M-Base   | 360           | 40000            | 56.30    | 59.19      | 25.22| 25.55| 2.88  | 0.00      | 28.19   |
 | **Nandi-Mini-150M-Base** | **150**       | 500          | 37.20| 52.32  | 28.57 | 28.86 | 2.58 | 4.27 | 25.63 |
+### Note
+Mobile-LLM model checkpoints are not publicly available; their results are reported directly from the original paper. All other models have been evaluated using `lm-eval` under a consistent setup.
 ## 🚀 Usage