Instructions to use pankajmathur/nanochat-d34-sft-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pankajmathur/nanochat-d34-sft-hf with Transformers:

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

pipe = pipeline("text-generation", model="pankajmathur/nanochat-d34-sft-hf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pankajmathur/nanochat-d34-sft-hf")
model = AutoModelForCausalLM.from_pretrained("pankajmathur/nanochat-d34-sft-hf")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pankajmathur/nanochat-d34-sft-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pankajmathur/nanochat-d34-sft-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pankajmathur/nanochat-d34-sft-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pankajmathur/nanochat-d34-sft-hf

SGLang

How to use pankajmathur/nanochat-d34-sft-hf 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 "pankajmathur/nanochat-d34-sft-hf" \
    --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": "pankajmathur/nanochat-d34-sft-hf",
		"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 "pankajmathur/nanochat-d34-sft-hf" \
        --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": "pankajmathur/nanochat-d34-sft-hf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pankajmathur/nanochat-d34-sft-hf with Docker Model Runner:
```
docker model run hf.co/pankajmathur/nanochat-d34-sft-hf
```

NanoChat D34 SFT - HuggingFace Format

This is the pankajmathur/nanochat-d34-finetuned converted to HuggingFace Transformers format.

Model Description

Model type: Causal Language Model
Language: English
License: Apache 2.0

Usage

Install Transformer Library from Github with nanochat support

!pip install -q git+https://github.com/huggingface/transformers.git

Use dedicated NanoChatForCausalLM and PreTrainedTokenizerFast packages from Transformer Library

import torch
from transformers import NanoChatForCausalLM, PreTrainedTokenizerFast

# Load the converted model and tokenizer
tokenizer = PreTrainedTokenizerFast.from_pretrained("pankajmathur/nanochat-d34-sft-hf")
model = NanoChatForCausalLM.from_pretrained(
    "pankajmathur/nanochat-d34-sft-hf",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Generate text
prompt = "Hello, who are you?"

inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].to(model.device)

with torch.no_grad():
    outputs = model.generate(
        input_ids,
        max_new_tokens=100,
        do_sample=True,
        temperature=0.7,
        top_p=0.9,
        pad_token_id=tokenizer.eos_token_id
    )

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(f"🤖 Response:\n{response}")

Source

Original checkpoint: pankajmathur/nanochat-d34-finetuned
Repository: nanochat

Citation

If you use this model, please cite accordingly.

Downloads last month: 1,163

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for pankajmathur/nanochat-d34-sft-hf

Base model

karpathy/nanochat-d34

Finetuned

pankajmathur/nanochat-d34-finetuned

Finetuned

(4)

this model

Finetunes

1 model

pankajmathur
/

nanochat-d34-sft-hf