Instructions to use nazdef/1gpu-llm-small-en-it-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nazdef/1gpu-llm-small-en-it-base with Transformers:

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

pipe = pipeline("text-generation", model="nazdef/1gpu-llm-small-en-it-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nazdef/1gpu-llm-small-en-it-base")
model = AutoModelForCausalLM.from_pretrained("nazdef/1gpu-llm-small-en-it-base")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nazdef/1gpu-llm-small-en-it-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nazdef/1gpu-llm-small-en-it-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nazdef/1gpu-llm-small-en-it-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nazdef/1gpu-llm-small-en-it-base

SGLang

How to use nazdef/1gpu-llm-small-en-it-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 "nazdef/1gpu-llm-small-en-it-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": "nazdef/1gpu-llm-small-en-it-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 "nazdef/1gpu-llm-small-en-it-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": "nazdef/1gpu-llm-small-en-it-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nazdef/1gpu-llm-small-en-it-base with Docker Model Runner:
```
docker model run hf.co/nazdef/1gpu-llm-small-en-it-base
```

1gpu-llm-small-en-it-base / release_note.md

nazdef

Add files using upload-large-folder tool

0982b30 verified 20 days ago

preview code

Raw

History Blame Contribute Delete

818 Bytes

	# 2026-06-23 - GPT2PreLN decay-only release (`step_8600`)

	This release publishes the current best `decay-only` GPT2PreLN checkpoint in the workspace.

	- parent checkpoint: `step_8000.pt`
	- parent run: `202606212315_fresh-gpt2small-gpt2preln-k20-wsd-lr2e-4-7k-final2e5-webwiki`
	- decay-only continuation run: `20260622_resume-gpt2small-gpt2preln-k20-wsds800-final2e5-webwiki-step8000-dense50`
	- released checkpoint: `step_8600.pt`

	Selection summary:
	- `7k` decay-only winner: `step_7500` with `val_loss_mixed = 4.8401`
	- `8k` decay-only winner: `step_8600` with `val_loss_mixed = 4.7964`
	- result: `step_8600` is the best decay-only checkpoint across both tails

	Recommended decoding preset:
	- `balanced`
	- `temperature = 0.8`
	- `top_k = 50`
	- `top_p = 0.95`
	- `repetition_penalty = 1.1`
	- `no_repeat_ngram_size = 0`