Instructions to use iamshnoo/combined_only_continent_with_metadata_1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iamshnoo/combined_only_continent_with_metadata_1b with Transformers:

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

pipe = pipeline("text-generation", model="iamshnoo/combined_only_continent_with_metadata_1b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iamshnoo/combined_only_continent_with_metadata_1b")
model = AutoModelForCausalLM.from_pretrained("iamshnoo/combined_only_continent_with_metadata_1b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iamshnoo/combined_only_continent_with_metadata_1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iamshnoo/combined_only_continent_with_metadata_1b"
# 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_only_continent_with_metadata_1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iamshnoo/combined_only_continent_with_metadata_1b

SGLang

How to use iamshnoo/combined_only_continent_with_metadata_1b 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_only_continent_with_metadata_1b" \
    --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_only_continent_with_metadata_1b",
		"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_only_continent_with_metadata_1b" \
        --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_only_continent_with_metadata_1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iamshnoo/combined_only_continent_with_metadata_1b with Docker Model Runner:
```
docker model run hf.co/iamshnoo/combined_only_continent_with_metadata_1b
```

iamshnoo commited on Apr 2

Commit

267eae4

verified ·

1 Parent(s): b58f7cb

Update model card from W&B metadata

Browse files

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -26,7 +26,9 @@ This repo contains the continent 1b model at the final 10k-step checkpoint for t
 ## Weights & Biases Provenance
-- Run: [23/03/2026_08:58:03_combined_only_continent_with_metadata_1b](https://wandb.ai/iamshnoo/nanotron/runs/6baqnhow)
 - State: `finished`
 - Runtime: `57h 18m 26s`
@@ -54,5 +56,6 @@ This repo contains the continent 1b model at the final 10k-step checkpoint for t
 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 01:19:24 UTC`

 ## Weights & Biases Provenance
+- Run name: `23/03/2026_08:58:03_combined_only_continent_with_metadata_1b`
+- Internal run URL: `https://wandb.ai/iamshnoo/nanotron/runs/6baqnhow`
+- Note: the Weights & Biases workspace is private; public readers should use the summarized metrics and configuration below.
 - State: `finished`
 - Runtime: `57h 18m 26s`
 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 13:49:54 UTC`