Instructions to use Allanatrix/Nexa-OLMo-sci7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Allanatrix/Nexa-OLMo-sci7b with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-7B")
model = PeftModel.from_pretrained(base_model, "Allanatrix/Nexa-OLMo-sci7b")

Transformers

How to use Allanatrix/Nexa-OLMo-sci7b with Transformers:

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

pipe = pipeline("text-generation", model="Allanatrix/Nexa-OLMo-sci7b")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Allanatrix/Nexa-OLMo-sci7b", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Allanatrix/Nexa-OLMo-sci7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Allanatrix/Nexa-OLMo-sci7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Allanatrix/Nexa-OLMo-sci7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Allanatrix/Nexa-OLMo-sci7b

SGLang

How to use Allanatrix/Nexa-OLMo-sci7b 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 "Allanatrix/Nexa-OLMo-sci7b" \
    --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": "Allanatrix/Nexa-OLMo-sci7b",
		"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 "Allanatrix/Nexa-OLMo-sci7b" \
        --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": "Allanatrix/Nexa-OLMo-sci7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Allanatrix/Nexa-OLMo-sci7b with Docker Model Runner:
```
docker model run hf.co/Allanatrix/Nexa-OLMo-sci7b
```

Model Card for nexa-OLMo-sci7b

Model Details

Model Description:
nexa-OLMo-sci7b is a fine-tuned variant of allenai/OLMo-7B, optimized for scientific research generation tasks such as hypothesis generation, abstract writing, and methodology completion. Fine-tuning was performed using PEFT with LoRA in 4-bit quantized mode via bitsandbytes.

Developed by: Allan (Independent Scientific Intelligence Architect)
Shared by: Allan (https://huggingface.co/allan-wandia)
Model type: Decoder-only transformer (causal language model)
Language(s): English (scientific domain-specific vocabulary)
License: Apache 2.0
Fine-tuned from: allenai/OLMo-7B
Repository: https://huggingface.co/allan-wandia/nexa-olmo-sci7b

Training Details

Training Data:

Size: 100 million tokens
Source: Curated scientific literature (Bio, Physics, QST, Astro)

Hyperparameters:

Sequence length: 1024
Batch size: 1
Gradient Accumulation Steps: 64
Effective Batch Size: 64
Learning rate: 2e-05
Epochs: 2
LoRA: Enabled (PEFT)
Quantization: 4-bit

Results:
Robust performance in scientific prose tasks, with novelty varying by prompt diversity.

Downloads last month: 2

Model tree for Allanatrix/Nexa-OLMo-sci7b

Base model

allenai/OLMo-7B

Adapter

(1)

this model

Dataset used to train Allanatrix/Nexa-OLMo-sci7b

Collection including Allanatrix/Nexa-OLMo-sci7b

Nexa_Models

Collection

This is where I keep all of my SciML models • 13 items • Updated Jul 22, 2025 • 1