olmo3-7b-medai-cpt_olddata

Instructions to use CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata with Transformers:

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

pipe = pipeline("text-generation", model="CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata")
model = AutoModelForCausalLM.from_pretrained("CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata

SGLang

How to use CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata 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/olmo3-7b-medai-cpt_olddata" \
    --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/olmo3-7b-medai-cpt_olddata",
		"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/olmo3-7b-medai-cpt_olddata" \
        --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/olmo3-7b-medai-cpt_olddata",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata with Docker Model Runner:
```
docker model run hf.co/CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata
```

olmo3-7b-medai-cpt

Continued pre-training (mid-training) of allenai/Olmo-3-1025-7B on the CaML corpus CompassioninMachineLearning/pretraining_research_documents_medai (revision 06248aa).

This repository is a server-side copy of ganscs/Olmo7b-olmo-a100-new-20260908-CPT-merged-step-750; weights, tokenizer and manifests are byte-identical to that upload (see merge_manifest.json for shard checksums).

Standalone BF16 model combining allenai/Olmo-3-1025-7B with the trained LoRA adapter and full embedding/output weights from checkpoint 750. Load this repository directly with Transformers; a separate PEFT adapter is not required.

Provenance

Base revision: a81bae42db3975be1671e27b9c9a56da1a9f980f.
Adapter repository revision: edba4e91735a37b3c886961e707355f3e541ef61.
Selected step: 750, the best validation checkpoint in this training run.
Source checkpoint training-time validation loss: 1.3001196.
rsLoRA rank 128, alpha 64.
The fully trained embed_tokens and lm_head weights replace the original endpoints.
The output uses the checkpoint tokenizer and the original base architecture/configuration.

Adapters were trained with a 4-bit base. This export merges them into the original BF16 base revision using PEFT's safe merge operation. The training-time validation score above is not a new evaluation of this BF16 export.

Validation

Every adapter tensor was consumed; all output tensors are finite and match the Transformers architecture's names and shapes. The model loaded locally without PEFT adapters and produced finite logits and a short greedy generation. merge_manifest.json records source hashes, merge details and output checksums; validation.json records the smoke test. training_manifest.json preserves the source experiment settings. This is a weights-only export, without optimizer state.

Load

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "CompassioninMachineLearning/olmo3-7b-medai-cpt"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id, dtype=torch.bfloat16, device_map="auto"
)

Downloads last month: 3

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata

Base model

allenai/Olmo-3-1025-7B

Finetuned

(62)

this model

olmo3-7b-medai-cpt

Provenance

Validation

Load

Model tree for CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata

Dataset used to train CompassioninMachineLearning/olmo3-7b-medai-cpt_olddata