Instructions to use RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15 with Transformers:

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

pipe = pipeline("text-generation", model="RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15")
model = AutoModelForCausalLM.from_pretrained("RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15

SGLang

How to use RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15 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 "RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15" \
    --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": "RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15",
		"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 "RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15" \
        --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": "RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15 with Docker Model Runner:
```
docker model run hf.co/RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

OLMo 3 7B — 15% GermanWeb

Annealing-only run from the pretrained Stage 1 weights. The HF optimizer is not imported; a fresh optimizer and scheduler are used.

Base model

allenai/Olmo-3-1025-7B at revision stage1-step1413814. These checkpoints are base models, not instruction-tuned or chat-tuned models.

Training data

annealing data: 15% GermanWeb — Exactly 12B tokens: 85% ClimbMix and 15% GermanWeb.

Training configuration

The repository contains checkpoint revisions named step-XXXXXXX; main is the final checkpoint. Optimizer states are not part of these HF exports. The exact source paths, revision mapping, and publication code are maintained in the private KletterMix_Ablations repository.

Downloads last month: -

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for RuHae/KletterMix-Ablations-OLMo3-7B-GermanWeb-15

Base model

allenai/Olmo-3-1025-7B

Finetuned

(96)

this model