Instructions to use GenerTeam/GENERator-eukaryote-1.2b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GenerTeam/GENERator-eukaryote-1.2b-base with Transformers:

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

pipe = pipeline("text-generation", model="GenerTeam/GENERator-eukaryote-1.2b-base", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GenerTeam/GENERator-eukaryote-1.2b-base", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("GenerTeam/GENERator-eukaryote-1.2b-base", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GenerTeam/GENERator-eukaryote-1.2b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GenerTeam/GENERator-eukaryote-1.2b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GenerTeam/GENERator-eukaryote-1.2b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GenerTeam/GENERator-eukaryote-1.2b-base

SGLang

How to use GenerTeam/GENERator-eukaryote-1.2b-base 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 "GenerTeam/GENERator-eukaryote-1.2b-base" \
    --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": "GenerTeam/GENERator-eukaryote-1.2b-base",
		"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 "GenerTeam/GENERator-eukaryote-1.2b-base" \
        --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": "GenerTeam/GENERator-eukaryote-1.2b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GenerTeam/GENERator-eukaryote-1.2b-base with Docker Model Runner:
```
docker model run hf.co/GenerTeam/GENERator-eukaryote-1.2b-base
```

GenerTeam commited on Mar 6, 2025

Commit

ac666ae

verified ·

1 Parent(s): 1538129

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ An issue was identified in the `model.safetensors` file of the initial release,
 ## Abouts
 In this repository, we present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs and 1.2B parameters, trained on an expansive dataset comprising 386 billion base pairs of eukaryotic DNA. Our evaluations demonstrate that the GENERator consistently achieves state-of-the-art performance across a wide spectrum of benchmarks, including [Genomic Benchmarks](https://huggingface.co/datasets/katielink/genomic-benchmarks/tree/main), [NT tasks](https://huggingface.co/datasets/InstaDeepAI/nucleotide_transformer_downstream_tasks_revised), and our newly proposed [Gener tasks](https://huggingface.co/GenerTeam).
-Beyond benchmark performance, the GENERator adheres to the central dogma of molecular biology, accurately generating protein-coding DNA sequences that produce proteins structurally analogous to known families. Moreover, the GENERator showcases significant promise in sequence optimization, particularly in the design of promoter sequences that regulate gene activity during various biological stages, highlighting its potential for a series of biologically significant tasks. Our findings position the GENERator as a vital resource for genomic research and biotechnological advancement.
 For more technical details, please refer to our paper [**GENERator: A Long-Context Generative Genomic Foundation Model**](https://huggingface.co/GenerTeam).

 ## Abouts
 In this repository, we present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs and 1.2B parameters, trained on an expansive dataset comprising 386 billion base pairs of eukaryotic DNA. Our evaluations demonstrate that the GENERator consistently achieves state-of-the-art performance across a wide spectrum of benchmarks, including [Genomic Benchmarks](https://huggingface.co/datasets/katielink/genomic-benchmarks/tree/main), [NT tasks](https://huggingface.co/datasets/InstaDeepAI/nucleotide_transformer_downstream_tasks_revised), and our newly proposed [Gener tasks](https://huggingface.co/GenerTeam).
+Beyond benchmark performance, the GENERator adheres to the central dogma of molecular biology, accurately generating protein-coding DNA sequences that produce proteins structurally analogous to known families. Moreover, the GENERator showcases significant promise in sequence optimization, particularly in the design of enhancer sequences that regulate gene expression during various biological stages, highlighting its potential for a series of biologically significant tasks. Our findings position the GENERator as a vital resource for genomic research and biotechnological advancement.
 For more technical details, please refer to our paper [**GENERator: A Long-Context Generative Genomic Foundation Model**](https://huggingface.co/GenerTeam).