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

Libraries

How to use nazdef/1gpu-llm-medium-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-medium-en-it-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

1gpu-llm-medium-en-it-base / source_losses.json

nazdef

release: publish official 1gpu-llm medium base from step14700

52ee5b8 verified 13 days ago

Raw

History Blame Contribute Delete

2.75 kB

	{
	"checkpoints": {
	"manual-manual-step_14700-14700": {
	"books_en": {
	"loss": 4.411039806547619,
	"num_batches": 1,
	"num_sequences": 1,
	"num_tokens": 21,
	"path": "/home/descanso/.openclaw/workspace/python_project/llm-nanochat/eval/pretrain/sources/books_en.jsonl",
	"perplexity": 82.35505232121704
	},
	"books_it": {
	"loss": 4.39037105015346,
	"num_batches": 1,
	"num_sequences": 1,
	"num_tokens": 21,
	"path": "/home/descanso/.openclaw/workspace/python_project/llm-nanochat/eval/pretrain/sources/books_it.jsonl",
	"perplexity": 80.67034617221599
	},
	"code": {
	"loss": 7.720833333333333,
	"num_batches": 1,
	"num_sequences": 1,
	"num_tokens": 30,
	"path": "/home/descanso/.openclaw/workspace/python_project/llm-nanochat/eval/pretrain/sources/code.jsonl",
	"perplexity": 2254.8378293808423
	},
	"web_en": {
	"loss": 5.489309210526316,
	"num_batches": 1,
	"num_sequences": 1,
	"num_tokens": 19,
	"path": "/home/descanso/.openclaw/workspace/python_project/llm-nanochat/eval/pretrain/sources/web_en.jsonl",
	"perplexity": 242.0899159175953
	},
	"web_it": {
	"loss": 5.4087171052631575,
	"num_batches": 1,
	"num_sequences": 1,
	"num_tokens": 19,
	"path": "/home/descanso/.openclaw/workspace/python_project/llm-nanochat/eval/pretrain/sources/web_it.jsonl",
	"perplexity": 223.34487584359522
	},
	"wiki_en": {
	"loss": 2.9984019886363638,
	"num_batches": 1,
	"num_sequences": 1,
	"num_tokens": 22,
	"path": "/home/descanso/.openclaw/workspace/python_project/llm-nanochat/eval/pretrain/sources/wiki_en.jsonl",
	"perplexity": 20.05346563890292
	},
	"wiki_it": {
	"loss": 2.92021484375,
	"num_batches": 1,
	"num_sequences": 1,
	"num_tokens": 25,
	"path": "/home/descanso/.openclaw/workspace/python_project/llm-nanochat/eval/pretrain/sources/wiki_it.jsonl",
	"perplexity": 18.54527136741806
	}
	}
	},
	"recommended_checkpoint": {
	"checkpoint_name": "step_14700",
	"checkpoint_path": "/mnt/apps/llm-nanochat/checkpoints/20260629_resume-gpt2medium-gpt2preln-k20-wsddecayonly-rerunmissing-lr3p5294e5-anchor20k-final2e5-webwiki-step14200-to14850/step_14700.pt",
	"direction": "min",
	"value": 4.443570063664363
	},
	"source_losses": {
	"books_en": 4.411039806547619,
	"books_it": 4.39037105015346,
	"code": 7.720833333333333,
	"web_en": 5.489309210526316,
	"web_it": 5.4087171052631575,
	"wiki_en": 2.9984019886363638,
	"wiki_it": 2.92021484375
	}
	}