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

Libraries

How to use iamshnoo/combined_with_metadata_chat with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iamshnoo/combined_with_metadata_chat")
model = AutoModelForCausalLM.from_pretrained("iamshnoo/combined_with_metadata_chat")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use iamshnoo/combined_with_metadata_chat 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_chat"
# 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_chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iamshnoo/combined_with_metadata_chat

SGLang

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

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

combined_with_metadata_chat

Summary

This repo contains the merged chat model for the combined with metadata branch of the metadata localization project. It was produced by supervised fine-tuning on the project QA benchmark after project pretraining.

Variant Metadata

Stage: sft_chat
Family: chat
Metadata condition: with_metadata
Base model lineage: combined_with_metadata_1b

Weights & Biases Provenance

Run name: still-dew-1
Internal run URL: https://wandb.ai/iamshnoo/huggingface/runs/x9ixdg0u
Note: the Weights & Biases workspace is private; public readers should use the summarized metrics and configuration below.
State: failed
Runtime: 3h 44m 45s

Run Summary

train/loss: 1.2337
train/global_step: 7,764
train/epoch: 3
train/learning_rate: 0
train/grad_norm: 0.0725

Training Configuration

per_device_train_batch_size: 2
gradient_accumulation_steps: 8
learning_rate: 0.0002
num_train_epochs: 3
optim: adamw_bnb_8bit
bf16: True
gradient_checkpointing: True
use_liger_kernel: True

SFT Notes

Fine-tuning method: PEFT / LoRA
Optimizer: adamw_bnb_8bit
bf16=True, gradient_checkpointing=True, use_liger_kernel=True
per_device_train_batch_size=2, gradient_accumulation_steps=8
LoRA targets: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj

Training Curves

Static plots below were exported from the private Weights & Biases run and embedded here for public access.

Train Loss

Learning Rate

Gradient Norm

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.

Training data source: News on the Web (NOW) Corpus
Project repository: https://github.com/iamshnoo/metadata_localization
Paper: https://arxiv.org/abs/2601.15236

Last synced: 2026-04-02 14:48:16 UTC

Downloads last month: 47

Safetensors

Model size

1B params

Tensor type

BF16

Collection including iamshnoo/combined_with_metadata_chat

Metadata Conditioned LLMs

Collection

Pretraining Data: English NOW corpus (english-corpora.org/now). Paper: arxiv.org/abs/2601.15236. Code: github.com/iamshnoo/metadata_localization • 92 items • Updated Apr 11

Paper for iamshnoo/combined_with_metadata_chat

Metadata Conditioned Large Language Models for Localization

Paper • 2601.15236 • Published Jan 21