Instructions to use submarat/gpt2-small-fineweb-edu-10b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use submarat/gpt2-small-fineweb-edu-10b-sft with Transformers:

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

pipe = pipeline("text-generation", model="submarat/gpt2-small-fineweb-edu-10b-sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("submarat/gpt2-small-fineweb-edu-10b-sft")
model = AutoModelForCausalLM.from_pretrained("submarat/gpt2-small-fineweb-edu-10b-sft", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use submarat/gpt2-small-fineweb-edu-10b-sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "submarat/gpt2-small-fineweb-edu-10b-sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "submarat/gpt2-small-fineweb-edu-10b-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/submarat/gpt2-small-fineweb-edu-10b-sft

SGLang

How to use submarat/gpt2-small-fineweb-edu-10b-sft 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 "submarat/gpt2-small-fineweb-edu-10b-sft" \
    --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": "submarat/gpt2-small-fineweb-edu-10b-sft",
		"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 "submarat/gpt2-small-fineweb-edu-10b-sft" \
        --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": "submarat/gpt2-small-fineweb-edu-10b-sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use submarat/gpt2-small-fineweb-edu-10b-sft with Docker Model Runner:
```
docker model run hf.co/submarat/gpt2-small-fineweb-edu-10b-sft
```

GPT-2 Small — instruction-tuned (SFT) toy assistant

Instruction-tuned version of submarat/gpt2-small-fineweb-edu-10b (a 124M GPT-2 reproduced from scratch on 10B FineWeb-Edu tokens), fine-tuned on Alpaca-cleaned with TRL's SFTTrainer (completion-only loss).

Interactive demo: https://huggingface.co/spaces/submarat/gpt2-fineweb-chat
Code: https://github.com/submarat/gpt2-small-repro (posttraining/)
Write-up: https://submarat.github.io/a-toy-assistant-sft-and-dpo/

It's a toy: at 124M it follows simple instructions and holds the format, but it's shallow and hallucinates confidently. That's the point — it's a hands-on pretrain → SFT pipeline, not a usable product.

Prompt format (Alpaca-style)

### Instruction:
{instruction}

### Response:

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

m = AutoModelForCausalLM.from_pretrained("submarat/gpt2-small-fineweb-edu-10b-sft")
tok = AutoTokenizer.from_pretrained("submarat/gpt2-small-fineweb-edu-10b-sft")

prompt = "### Instruction:\nList three tips for staying focused while studying.\n\n### Response:\n"
ids = tok(prompt, return_tensors="pt").input_ids
out = m.generate(ids, max_new_tokens=80, do_sample=True, top_k=40, temperature=0.7,
                 repetition_penalty=1.3, pad_token_id=tok.eos_token_id)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))

Training

Base: submarat/gpt2-small-fineweb-edu-10b (124M, exact-GELU)
Data: Alpaca-cleaned (~52k), formatted as prompt/completion; loss on the response only
3 epochs, batch 64, LR 2e-5 cosine, bf16, ctx 512

Trained alongside a DPO variant, submarat/gpt2-small-fineweb-edu-10b-dpo.

Downloads last month: 44

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for submarat/gpt2-small-fineweb-edu-10b-sft

Base model

submarat/gpt2-small-fineweb-edu-10b

Quantized

(2)

this model

Quantizations

1 model

submarat
/

gpt2-small-fineweb-edu-10b-sft

GPT-2 Small — instruction-tuned (SFT) toy assistant

Prompt format (Alpaca-style)

Usage

Training

Model tree for submarat/gpt2-small-fineweb-edu-10b-sft

Dataset used to train submarat/gpt2-small-fineweb-edu-10b-sft

Space using submarat/gpt2-small-fineweb-edu-10b-sft 1