Instructions to use CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1 with Transformers:

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

pipe = pipeline("text-generation", model="CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1")
model = AutoModelForCausalLM.from_pretrained("CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1

SGLang

How to use CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1 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 "CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1" \
    --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": "CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1",
		"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 "CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1" \
        --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": "CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1 with Docker Model Runner:
```
docker model run hf.co/CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1
```

Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1

Standalone merged BF16 model from epoch 1.0, step 375.

Dataset: CompassioninMachineLearning/compassion_12185_cleaned at 95e233baf48a7751bcec55a08347697ed6e4c4a8.

Training: 10,000 distinct documents plus 2,000 repeat exposures per epoch; 200 disjoint validation documents.

Merged with Unsloth's native save_pretrained_merged(save_method="merged_16bit"). Weights are validated BF16 and packaged losslessly into eight safetensors shards. No adapter is required to load this model.

See run_manifest.json for base revision, document selection hashes, training parameters and export validation. Training does not establish an improvement in compassion; evaluate that separately.

Downloads last month: -

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1

Base model

allenai/Olmo-3-1025-7B

Finetuned

(66)

this model

CompassioninMachineLearning
/

Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1

Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1

Model tree for CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1

Dataset used to train CompassioninMachineLearning/Olmo7b-compassion-cleaned-10k-20260910-CPT-merged-epoch-1