Instructions to use brettleehari/cricketmind-nemotron-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use brettleehari/cricketmind-nemotron-mini with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("brettleehari/cricketmind-nemotron-mini")
model = AutoModelForCausalLM.from_pretrained("brettleehari/cricketmind-nemotron-mini")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use brettleehari/cricketmind-nemotron-mini with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/brettleehari/cricketmind-nemotron-mini

SGLang

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

Docker Model Runner
How to use brettleehari/cricketmind-nemotron-mini with Docker Model Runner:
```
docker model run hf.co/brettleehari/cricketmind-nemotron-mini
```

CricketMind — Cricket Domain Expert (Nemotron Mini 4B)

A fine-tuned version of nvidia/Nemotron-Mini-4B-Instruct specialized in MCC Laws of Cricket and match situation analysis.

Training

Method: LoRA (r=16, alpha=32) on bfloat16
Target modules: q_proj, v_proj
Data: ~170 examples — Laws QA + response distillation from Claude
Hardware: NVIDIA A100 80GB SXM
Epochs: 3
Final training loss: 1.65

Evaluation — CricketBench v0.1

LLM-as-judge evaluation (Claude) across 20 questions in 4 categories:

Category	CricketMind	Baseline Nemotron	Improvement
Laws Recall (30%)	60.0%	40%	+20pp
Conditional Reasoning (35%)	70.0%	25%	+45pp
Match Situation (25%)	80.0%	30%	+50pp
Edge Case (10%)	50.0%	20%	+30pp
Overall	67.5%	30.2%	+37.3pp

Usage

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "brettleehari/cricketmind-nemotron-mini"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

prompt = """### Instruction:
You are CricketMind, an expert in the Laws of Cricket. Cite Law numbers and reason step by step.

### Input:
A batter is struck on the pad outside the line of off stump. They played a shot. Is it out LBW?

### Response:
"""

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.1)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Google Colab (free GPU)

Go to colab.google.com → New notebook
Runtime → Change runtime type → T4 GPU
Paste the code above and run

Dataset

Training data and evaluation suite: brettleehari/cricketbench-v1

Author

Hariprasad Sudharshan — AI Product Manager

Downloads last month: 4

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for brettleehari/cricketmind-nemotron-mini

Base model

nvidia/Nemotron-Mini-4B-Instruct

Adapter

(28)

this model

Dataset used to train brettleehari/cricketmind-nemotron-mini

Evaluation results

Overall CricketBench Score on CricketBench v0.1
self-reported

67.500