Instructions to use iamshnoo/combined_with_metadata_3b_step4k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iamshnoo/combined_with_metadata_3b_step4k with Transformers:

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

pipe = pipeline("text-generation", model="iamshnoo/combined_with_metadata_3b_step4k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("iamshnoo/combined_with_metadata_3b_step4k")
model = AutoModelForMultimodalLM.from_pretrained("iamshnoo/combined_with_metadata_3b_step4k")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iamshnoo/combined_with_metadata_3b_step4k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iamshnoo/combined_with_metadata_3b_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_with_metadata_3b_step4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iamshnoo/combined_with_metadata_3b_step4k

SGLang

How to use iamshnoo/combined_with_metadata_3b_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_with_metadata_3b_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_with_metadata_3b_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_with_metadata_3b_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_with_metadata_3b_step4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iamshnoo/combined_with_metadata_3b_step4k with Docker Model Runner:
```
docker model run hf.co/iamshnoo/combined_with_metadata_3b_step4k
```

iamshnoo commited on Apr 2

Commit

cb6f80a

verified ·

1 Parent(s): 987167c

Update model card and embedded training curves

Browse files

Files changed (4) hide show

README.md +19 -3
assets/tokens_per_sec.png +0 -0
assets/train_loss.png +0 -0
assets/val_perplexity.png +0 -0

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ tags:
 - global
 - 3b
 - with-metadata
-- continued-pretraining
 - intermediate-checkpoint
 ---
@@ -15,7 +15,7 @@ tags:
 ## Summary
-This repo contains the global combined model exported from the 4k checkpoint for the metadata localization project. It comes from continued pretraining of a Llama 3.2 base model on the project corpus.
 ## Variant Metadata
@@ -53,6 +53,22 @@ This repo contains the global combined model exported from the 4k checkpoint for
 - `min_decay_lr`: `0`
 - `checkpoint_interval`: `100`
 ## Project Context
 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).
@@ -60,4 +76,4 @@ This model is part of the metadata localization release. Related checkpoints and
 - 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 13:49:13 UTC`

 - global
 - 3b
 - with-metadata
+- pretraining
 - intermediate-checkpoint
 ---
 ## Summary
+This repo contains the global combined model exported from the 4k checkpoint for the metadata localization project. It was trained from scratch on the project corpus, using the Llama 3.2 tokenizer and vocabulary.
 ## Variant Metadata
 - `min_decay_lr`: `0`
 - `checkpoint_interval`: `100`
+## Training Curves
+Static plots below were exported from the private Weights & Biases run and embedded here for public access.
+### Train Loss
+![Train Loss](assets/train_loss.png)
+### Validation Perplexity
+![Validation Perplexity](assets/val_perplexity.png)
+### Throughput
+![Throughput](assets/tokens_per_sec.png)
 ## Project Context
 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).
 - 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 14:40:12 UTC`

assets/tokens_per_sec.png ADDED Viewed

assets/train_loss.png ADDED Viewed

assets/val_perplexity.png ADDED Viewed