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")

# pip install -U transformers accelerate
# 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_olddata

File size: 2,780 Bytes

---
language: en
library_name: transformers
pipeline_tag: text-generation
base_model: allenai/Olmo-3-1025-7B
license: apache-2.0
datasets:
- CompassioninMachineLearning/pretraining_research_documents_medai
tags:
- mid-training
- merged
- continued-pretraining
- bfloat16
---

# olmo3-7b-medai-cpt

Continued pre-training (mid-training) of `allenai/Olmo-3-1025-7B` on the CaML corpus
[`CompassioninMachineLearning/pretraining_research_documents_medai`](https://huggingface.co/datasets/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`](https://huggingface.co/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](https://huggingface.co/ganscs/Olmo7b-olmo-a100-new-20260908-CPT-LoRA-checkpoints/tree/edba4e91735a37b3c886961e707355f3e541ef61/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

```python
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"
)
```