Instructions to use NILKNARFGonzo/single-floppy-346k-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NILKNARFGonzo/single-floppy-346k-base with Transformers:

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

pipe = pipeline("text-generation", model="NILKNARFGonzo/single-floppy-346k-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NILKNARFGonzo/single-floppy-346k-base")
model = AutoModelForCausalLM.from_pretrained("NILKNARFGonzo/single-floppy-346k-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NILKNARFGonzo/single-floppy-346k-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NILKNARFGonzo/single-floppy-346k-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NILKNARFGonzo/single-floppy-346k-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NILKNARFGonzo/single-floppy-346k-base

SGLang

How to use NILKNARFGonzo/single-floppy-346k-base 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 "NILKNARFGonzo/single-floppy-346k-base" \
    --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": "NILKNARFGonzo/single-floppy-346k-base",
		"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 "NILKNARFGonzo/single-floppy-346k-base" \
        --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": "NILKNARFGonzo/single-floppy-346k-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NILKNARFGonzo/single-floppy-346k-base with Docker Model Runner:
```
docker model run hf.co/NILKNARFGonzo/single-floppy-346k-base
```

A weird model trained on a Pi.

Training Details

Category	Specification
Model Architecture	GPT‑2 (decoder‑only Transformer)
Total Parameters	346,104
Model Size (FP32)	1.32 MB (1,387,072 bytes)
Layers (`n_layer`)	2
Embedding Dimension (`n_embd`)	92
Attention Heads (`n_head`)	2
Context Length (`n_positions`)	1024
Vocabulary Size	502 (byte‑level BPE, tied embeddings)
Training Framework	Oobabooga TextGen WebUI (Transformers + PEFT)
Fine‑Tuning Method	LoRA (Target all linear layers)
LoRA Rank	8
LoRA Alpha	16
Optimizer	AdamW 8‑bit (`adamw_bnb_8bit`)
Learning Rate	2e‑4 (linear scheduler, 20 warmup steps)
Batch Size	4
Training Dataset	Capybara ShareGPT (random subset, 1.36 MB, 1,453,408 bytes)
Dataset Format	JSON array with `"text"` field (flattened ShareGPT)
Training Epochs	5
Loss Target	Stopped at ~6.0 (plateaued due to parameter limit)
Hardware	Raspberry Pi 5, 8GB RAM, ARM Cortex‑A76 (CPU only)
Training Time	~1 hour
Tokenizer	Custom byte‑level BPE (trained on dataset)
Tokenizer Special Tokens	`[BOS]`, `[EOS]`, `[PAD]`, `[UNK]`
Note	This is a proof‑of‑concept model. It fits on a 3.5‑inch floppy disk and was trained from scratch on a Raspberry Pi.

HUMONGOUS NOTE: This model is a base model. The LoRA is provided separately, and this base model is essentially a tiny random model without it.

Downloads last month: 24

Safetensors

Model size

346k params

Tensor type

F32

Model tree for NILKNARFGonzo/single-floppy-346k-base

Finetunes

1 model

NILKNARFGonzo
/

single-floppy-346k-base

Training Details

Model tree for NILKNARFGonzo/single-floppy-346k-base

Dataset used to train NILKNARFGonzo/single-floppy-346k-base