Text Generation
Transformers
Safetensors
English
gpt2
novi
novi-nano
novi-nano-instruct
causal-lm
from-scratch
instruction-tuning
chatml
conversational
text-generation-inference
Instructions to use Novi-AI/Novi-Nano-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Novi-AI/Novi-Nano-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Novi-AI/Novi-Nano-Instruct") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Novi-AI/Novi-Nano-Instruct") model = AutoModelForCausalLM.from_pretrained("Novi-AI/Novi-Nano-Instruct", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Novi-AI/Novi-Nano-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Novi-AI/Novi-Nano-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": "Novi-AI/Novi-Nano-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Novi-AI/Novi-Nano-Instruct
- SGLang
How to use Novi-AI/Novi-Nano-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 "Novi-AI/Novi-Nano-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": "Novi-AI/Novi-Nano-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 "Novi-AI/Novi-Nano-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": "Novi-AI/Novi-Nano-Instruct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Novi-AI/Novi-Nano-Instruct with Docker Model Runner:
docker model run hf.co/Novi-AI/Novi-Nano-Instruct
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,8 @@ tags:
|
|
| 12 |
- from-scratch
|
| 13 |
- instruction-tuning
|
| 14 |
- chatml
|
|
|
|
|
|
|
| 15 |
---
|
| 16 |
|
| 17 |
# Novi-Nano-Instruct
|
|
@@ -222,4 +224,4 @@ This model is released under the **Apache 2.0** license.
|
|
| 222 |
|
| 223 |
Novi-Nano-Instruct explores instruction tuning at an extremely small scale, with just **1.26 million parameters** and **500 training examples**.
|
| 224 |
|
| 225 |
-
It is intentionally tiny — exploring how far instruction following can go with a fraction of the parameters used by modern LLMs.
|
|
|
|
| 12 |
- from-scratch
|
| 13 |
- instruction-tuning
|
| 14 |
- chatml
|
| 15 |
+
datasets:
|
| 16 |
+
- Novi-AI/Novi-510x
|
| 17 |
---
|
| 18 |
|
| 19 |
# Novi-Nano-Instruct
|
|
|
|
| 224 |
|
| 225 |
Novi-Nano-Instruct explores instruction tuning at an extremely small scale, with just **1.26 million parameters** and **500 training examples**.
|
| 226 |
|
| 227 |
+
It is intentionally tiny — exploring how far instruction following can go with a fraction of the parameters used by modern LLMs.
|