Instructions to use ClosRise/RandomNandi_200m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ClosRise/RandomNandi_200m with Transformers:

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

pipe = pipeline("text-generation", model="ClosRise/RandomNandi_200m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ClosRise/RandomNandi_200m")
model = AutoModelForCausalLM.from_pretrained("ClosRise/RandomNandi_200m")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ClosRise/RandomNandi_200m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ClosRise/RandomNandi_200m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ClosRise/RandomNandi_200m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ClosRise/RandomNandi_200m

SGLang

How to use ClosRise/RandomNandi_200m 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 "ClosRise/RandomNandi_200m" \
    --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": "ClosRise/RandomNandi_200m",
		"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 "ClosRise/RandomNandi_200m" \
        --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": "ClosRise/RandomNandi_200m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ClosRise/RandomNandi_200m with Docker Model Runner:
```
docker model run hf.co/ClosRise/RandomNandi_200m
```

RandomNandi_200m

File size: 457 Bytes

9c87b6a

{
  "add_prefix_space": null,
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_nandi.NandiTokenizer",
      null
    ]
  },
  "backend": "tokenizers",
  "bos_token": "<|im_start|>",
  "bos_token_id": 1,
  "eos_token": "<|endoftext|>",
  "eos_token_id": 0,
  "is_local": false,
  "merges_file": null,
  "model_max_length": 2048,
  "pad_token": "<|pad|>",
  "pad_token_id": 3,
  "tokenizer_class": "NandiTokenizer",
  "unk_token": "<|endoftext|>"
}