Instructions to use iamshnoo/combined_no_europe_without_metadata_1b_step4k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iamshnoo/combined_no_europe_without_metadata_1b_step4k with Transformers:

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

pipe = pipeline("text-generation", model="iamshnoo/combined_no_europe_without_metadata_1b_step4k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iamshnoo/combined_no_europe_without_metadata_1b_step4k")
model = AutoModelForCausalLM.from_pretrained("iamshnoo/combined_no_europe_without_metadata_1b_step4k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iamshnoo/combined_no_europe_without_metadata_1b_step4k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iamshnoo/combined_no_europe_without_metadata_1b_step4k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iamshnoo/combined_no_europe_without_metadata_1b_step4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iamshnoo/combined_no_europe_without_metadata_1b_step4k

SGLang

How to use iamshnoo/combined_no_europe_without_metadata_1b_step4k 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 "iamshnoo/combined_no_europe_without_metadata_1b_step4k" \
    --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": "iamshnoo/combined_no_europe_without_metadata_1b_step4k",
		"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 "iamshnoo/combined_no_europe_without_metadata_1b_step4k" \
        --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": "iamshnoo/combined_no_europe_without_metadata_1b_step4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iamshnoo/combined_no_europe_without_metadata_1b_step4k with Docker Model Runner:
```
docker model run hf.co/iamshnoo/combined_no_europe_without_metadata_1b_step4k
```

iamshnoo commited on Apr 2

Commit

14b2e5b

verified ·

1 Parent(s): 4436389

Update model card from W&B metadata

Browse files

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -28,7 +28,9 @@ This repo contains the leave out europe 1b step4k model exported from the 4k che
 ## Weights & Biases Provenance
-- Run: [25/12/2025_04:20:04_combined_no_europe_without_metadata_1b](https://wandb.ai/iamshnoo/nanotron/runs/wuszx8bw)
 - State: `finished`
 - Runtime: `114h 50m 7s`
@@ -56,5 +58,6 @@ This repo contains the leave out europe 1b step4k model exported from the 4k che
 This model is part of the metadata localization release. Related checkpoints and variants are grouped in the public Hugging Face collection [Metadata Conditioned LLMs](https://huggingface.co/collections/iamshnoo/metadata-conditioned-llms).
 - Training data source: [News on the Web (NOW) Corpus](https://www.english-corpora.org/now/)
 - Project repository: [https://github.com/iamshnoo/metadata_localization](https://github.com/iamshnoo/metadata_localization)
-Last synced: `2026-04-02 01:21:06 UTC`

 ## Weights & Biases Provenance
+- Run name: `25/12/2025_04:20:04_combined_no_europe_without_metadata_1b`
+- Internal run URL: `https://wandb.ai/iamshnoo/nanotron/runs/wuszx8bw`
+- Note: the Weights & Biases workspace is private; public readers should use the summarized metrics and configuration below.
 - State: `finished`
 - Runtime: `114h 50m 7s`
 This model is part of the metadata localization release. Related checkpoints and variants are grouped in the public Hugging Face collection [Metadata Conditioned LLMs](https://huggingface.co/collections/iamshnoo/metadata-conditioned-llms).
 - Training data source: [News on the Web (NOW) Corpus](https://www.english-corpora.org/now/)
 - Project repository: [https://github.com/iamshnoo/metadata_localization](https://github.com/iamshnoo/metadata_localization)
+- Paper: [https://arxiv.org/abs/2601.15236](https://arxiv.org/abs/2601.15236)
+Last synced: `2026-04-02 13:51:11 UTC`