Instructions to use macadeliccc/gemma-2b-pubmed-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use macadeliccc/gemma-2b-pubmed-classifier with Transformers:

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

pipe = pipeline("text-generation", model="macadeliccc/gemma-2b-pubmed-classifier")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("macadeliccc/gemma-2b-pubmed-classifier")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/gemma-2b-pubmed-classifier")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use macadeliccc/gemma-2b-pubmed-classifier with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "macadeliccc/gemma-2b-pubmed-classifier"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "macadeliccc/gemma-2b-pubmed-classifier",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/macadeliccc/gemma-2b-pubmed-classifier

SGLang

How to use macadeliccc/gemma-2b-pubmed-classifier 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 "macadeliccc/gemma-2b-pubmed-classifier" \
    --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": "macadeliccc/gemma-2b-pubmed-classifier",
		"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 "macadeliccc/gemma-2b-pubmed-classifier" \
        --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": "macadeliccc/gemma-2b-pubmed-classifier",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use macadeliccc/gemma-2b-pubmed-classifier with Docker Model Runner:
```
docker model run hf.co/macadeliccc/gemma-2b-pubmed-classifier
```

This lora was made for educational purposes as part of an upcoming series. The model returns a series of classifications in CSV. More information will be released 7/1

I make no claims about medical accuracy.

Trained on owaiskha9654/PubMed_MultiLabel_Text_Classification_Dataset_MeSH

Prompt Template:

<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant

Example Usage

System: Given the title and abstract of a medical research paper, classify it into the most relevant MeSH (Medical Subject Headings) major terms.

Input: Title: Expression of p53 and coexistence of HPV in premalignant lesions and in cervical cancer. \n Abstract: Fifty-four paraffin embedded tissue sections from patients with dysplasia (21 cases) and with cervical cancer (33 cases) were analysed. HPV was detected and identified in two stages. Firstly, using mixed starters, chosen genomic DNA sequences were amplified; secondly the material thus obtained was analyzed by hybridization method using oligonucleotyde 31-P labelled probe. HPVs of type 6, 11, 16, 18, 33 were identified.

Output: Cervical Intraepithelial Neoplasia, DNA, Viral, Female, Humans, Precancerous Conditions, Tumor Suppressor Protein p53, Viral Load, Virology

Downloads last month: 7

Model tree for macadeliccc/gemma-2b-pubmed-classifier

Base model

google/gemma-2b

Quantized

(35)

this model

Dataset used to train macadeliccc/gemma-2b-pubmed-classifier

Collection including macadeliccc/gemma-2b-pubmed-classifier

Gemma-2b Loras

Collection

This collection is a suite of Gemma-2b loras that are trained on a variety of tasks. These were created for education purposes and aren't perfect • 4 items • Updated Mar 2 • 1