Instructions to use PursuitOfDataScience/Argonne-2.5-ctx13568 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PursuitOfDataScience/Argonne-2.5-ctx13568 with Transformers:

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

pipe = pipeline("text-generation", model="PursuitOfDataScience/Argonne-2.5-ctx13568")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PursuitOfDataScience/Argonne-2.5-ctx13568", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PursuitOfDataScience/Argonne-2.5-ctx13568 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PursuitOfDataScience/Argonne-2.5-ctx13568"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PursuitOfDataScience/Argonne-2.5-ctx13568",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PursuitOfDataScience/Argonne-2.5-ctx13568

SGLang

How to use PursuitOfDataScience/Argonne-2.5-ctx13568 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 "PursuitOfDataScience/Argonne-2.5-ctx13568" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PursuitOfDataScience/Argonne-2.5-ctx13568",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "PursuitOfDataScience/Argonne-2.5-ctx13568" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PursuitOfDataScience/Argonne-2.5-ctx13568",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PursuitOfDataScience/Argonne-2.5-ctx13568 with Docker Model Runner:
```
docker model run hf.co/PursuitOfDataScience/Argonne-2.5-ctx13568
```

Argonne-2.5-ctx13568

Argonne-2.5-ctx13568 is a long-context continuation of PursuitOfDataScience/Argonne2.5-base.

Model architecture

Component	Specification
Parameters	1,273,807,360
Layers	28 transformer blocks
Hidden size	1,792
Attention heads	14 query / 7 key-value (GQA)
Context length	13,568 tokens
Vocabulary size	151,669
Position encoding	RoPE (θ = 10,000)

Training details

Item	Value
Start checkpoint	PursuitOfDataScience/Argonne2.5-base
Long-context tokens trained	16.0B tokens
Final cumulative tokens	92,050,960,384
Batch size per GPU	4
Gradient accumulation	1
Effective batch	108,544 tokens
Precision	bf16 autocast
Checkpoint dtype	bfloat16
Weight format	3 sharded safetensors

Long-context data

Dataset source: allenai/dolma3_longmino_pool
Selected subset: 16k-32k LongMino pool
Kept documents: 4,595,978
Kept tokens (Qwen tokenizer): 105,223,923,033
This release used the long-context stage only (no additional short-context stage in this run).

Tokenizer

This model uses the Qwen3 tokenizer family via the Qwen2Tokenizer compatibility class.

Source code

The release was built from the GitHub main branch codebase: https://github.com/PursuitOfDataScience/ArgonneAI/tree/main

Key scripts:

midtraining.py

Loss curve

Inference

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "PursuitOfDataScience/Argonne-2.5-ctx13568"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    dtype=torch.bfloat16,
)

prompt = "Write a short paragraph about scientific computing at Argonne National Laboratory."
inputs = tokenizer(prompt, return_tensors="pt")
input_ids = inputs["input_ids"].to(model.device)

output_ids = model.generate(
    input_ids,
    max_length=input_ids.shape[1] + 256,
    temperature=0.8,
    top_p=0.9,
    top_k=50,
    do_sample=True,
)
print(tokenizer.decode(output_ids[0], skip_special_tokens=True))

Usage notes

Load with trust_remote_code=True.
max_position_embeddings is 13,568.
Weights are published as 3 bf16 safetensor shards.

References

Base checkpoint: PursuitOfDataScience/Argonne2.5-base
Long-context dataset: allenai/dolma3_longmino_pool

Citation

@misc{argonne25ctx13568,
  author = {PursuitOfDataScience},
  title = {Argonne-2.5-ctx13568},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/PursuitOfDataScience/Argonne-2.5-ctx13568}
}

Downloads last month: 30

Model tree for PursuitOfDataScience/Argonne-2.5-ctx13568

Finetunes

2 models

Collection including PursuitOfDataScience/Argonne-2.5-ctx13568

ArgonneAI

Collection

Pretrained LLMs from scratch. • 8 items • Updated 29 days ago • 1