Instructions to use FrontiersMind/Nandi-Mini-600M-Early-Checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FrontiersMind/Nandi-Mini-600M-Early-Checkpoint with Transformers:

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

pipe = pipeline("text-generation", model="FrontiersMind/Nandi-Mini-600M-Early-Checkpoint", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FrontiersMind/Nandi-Mini-600M-Early-Checkpoint", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FrontiersMind/Nandi-Mini-600M-Early-Checkpoint with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FrontiersMind/Nandi-Mini-600M-Early-Checkpoint"
# 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-600M-Early-Checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FrontiersMind/Nandi-Mini-600M-Early-Checkpoint

SGLang

How to use FrontiersMind/Nandi-Mini-600M-Early-Checkpoint 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-600M-Early-Checkpoint" \
    --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-600M-Early-Checkpoint",
		"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-600M-Early-Checkpoint" \
        --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-600M-Early-Checkpoint",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FrontiersMind/Nandi-Mini-600M-Early-Checkpoint with Docker Model Runner:
```
docker model run hf.co/FrontiersMind/Nandi-Mini-600M-Early-Checkpoint
```

vishesh-t27 commited on 8 days ago

Commit

a522301

verified ·

1 Parent(s): ede3ae3

Update README.md

Browse files

Files changed (1) hide show

README.md +19 -11

README.md CHANGED Viewed

@@ -20,7 +20,8 @@ library_name: transformers
 ## Introduction
-Nandi-Mini-500M-Early-Checkpoint is an early-stage checkpoint from the upcoming **Nandi-Mini-500M** model family — a compact multilingual language model focused on strong efficiency, deployment flexibility, and Indic language support.
 The model is being trained completely from scratch and is designed to deliver strong performance at low compute and memory budgets. This checkpoint is shared to provide an early look into the model’s scaling behavior and training progress.
@@ -99,7 +100,7 @@ This remains an active research area within the Nandi model family, and we plan
 - Type: Causal Language Model
 - Training Stage: Early Pretraining Checkpoint
-- Parameters: ~500M
 - Architecture: Transformer decoder
 - Positional Encoding: RoPE
 - Normalization: RMSNorm + QK Norm
@@ -159,12 +160,12 @@ The model is trained on English and a diverse set of Indic languages, including:
 # 🚀 Usage
 ```python
-!pip install transformers
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
-model_name = "FrontiersMind/Nandi-mini-500M-Early-Checkpoint"
 tokenizer = AutoTokenizer.from_pretrained(
     model_name,
@@ -178,6 +179,10 @@ model = AutoModelForCausalLM.from_pretrained(
     torch_dtype=torch.bfloat16
 ).eval()
 prompt = """
 The night was quiet and the streets were empty.
 A single light flickered in the distance.
@@ -190,13 +195,16 @@ model_inputs = tokenizer(
 ).to(model.device)
 outputs = model.generate(
-    **model_inputs,
-    max_new_tokens=64,
-    do_sample=True,
-    temperature=0.7,
-    top_p=0.95,
-    repetition_penalty=1.1
-)
 response = tokenizer.decode(
     outputs[0],

 ## Introduction
+Nandi-Mini-600M-Early-Checkpoint is an early-stage checkpoint from the upcoming **Nandi-Mini-600M** model family — a compact multilingual language model focused on strong efficiency, deployment flexibility, and Indic language support.
 The model is being trained completely from scratch and is designed to deliver strong performance at low compute and memory budgets. This checkpoint is shared to provide an early look into the model’s scaling behavior and training progress.
 - Type: Causal Language Model
 - Training Stage: Early Pretraining Checkpoint
+- Parameters: ~600M
 - Architecture: Transformer decoder
 - Positional Encoding: RoPE
 - Normalization: RMSNorm + QK Norm
 # 🚀 Usage
 ```python
+!pip install transformers=='5.4.0'
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
+model_name = "FrontiersMind/Nandi-Mini-600M-Early-Checkpoint"
 tokenizer = AutoTokenizer.from_pretrained(
     model_name,
     torch_dtype=torch.bfloat16
 ).eval()
+model.config.kv_cache_mode = "shared"
+# model.config.kv_cache_mode = "vanilla"
 prompt = """
 The night was quiet and the streets were empty.
 A single light flickered in the distance.
 ).to(model.device)
 outputs = model.generate(
+        **model_inputs,
+        max_new_tokens=50,
+        do_sample=False,
+        temperature=0.3,
+        top_k=20,
+        top_p=0.95,
+        repetition_penalty=1.1,
+        pad_token_id=tokenizer.eos_token_id,
+        use_cache=True,   # Disable KV cache
+    )
 response = tokenizer.decode(
     outputs[0],