Instructions to use ncbi/Gene-R1-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ncbi/Gene-R1-8B with Transformers:

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

pipe = pipeline("text-generation", model="ncbi/Gene-R1-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ncbi/Gene-R1-8B")
model = AutoModelForCausalLM.from_pretrained("ncbi/Gene-R1-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ncbi/Gene-R1-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ncbi/Gene-R1-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ncbi/Gene-R1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ncbi/Gene-R1-8B

SGLang

How to use ncbi/Gene-R1-8B 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 "ncbi/Gene-R1-8B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ncbi/Gene-R1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ncbi/Gene-R1-8B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ncbi/Gene-R1-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ncbi/Gene-R1-8B with Docker Model Runner:
```
docker model run hf.co/ncbi/Gene-R1-8B
```

zz07 commited on 4 days ago

Commit

be0b5fa

verified ·

1 Parent(s): 700af5d

Update README.md

Browse files

Files changed (1) hide show

README.md +41 -10

README.md CHANGED Viewed

@@ -1,17 +1,18 @@
 ---
 license: other
-license_name: public-domain
-license_link: LICENSE
 language:
 - en
 base_model:
-- meta-llama/Llama-3.1-8B-Instruct
 - meta-llama/Llama-3.2-1B-Instruct
 - meta-llama/Llama-3.2-3B-Instruct
-tags:
-- GSA
-pipeline_tag: text-generation
-library_name: transformers
 ---
 # Overview of Gene-R1
@@ -35,16 +36,33 @@ The model contains three versions:
 ```python
   import transformers
   from transformers import AutoTokenizer, AutoModelForCausalLM
   tokenizer_test = AutoTokenizer.from_pretrained(
-      model_path = "xxxxxxxxx", # The local path where the model is located
       token = "xxxxxxxxx" # Your access key of hugging face
   )
   model_test = AutoModelForCausalLM.from_pretrained(
-      model_path = "xxxxxxxxx", # The local path where the model is located
       device_map = "auto",
       token = "xxxxxxxxx" # Your access key of hugging face
   )
   def complete_chat(system, prompt, model, tokenizer):
       model.generation_config.do_sample=False
@@ -110,6 +128,19 @@ The expected output looks like:
 More details of model usage can be referred at our GitHub: [GitHub](https://github.com/ncbi-nlp/Gene-R1)
 # Acknowledgments
 This research was supported in part by the Intramural Research Program of the National Institutes of Health (NIH).

 ---
 license: other
+library_name: transformers
+pipeline_tag: text-generation
 language:
 - en
+tags:
+- gene-set-analysis
+- biomedical
+- reasoning
+- llama
 base_model:
 - meta-llama/Llama-3.2-1B-Instruct
 - meta-llama/Llama-3.2-3B-Instruct
+- meta-llama/Llama-3.1-8B-Instruct
 ---
 # Overview of Gene-R1
 ```python
   import transformers
   from transformers import AutoTokenizer, AutoModelForCausalLM
+  model_id = "ncbi/Gene-R1"
   tokenizer_test = AutoTokenizer.from_pretrained(
+      model_id,
       token = "xxxxxxxxx" # Your access key of hugging face
   )
   model_test = AutoModelForCausalLM.from_pretrained(
+      model_id,
       device_map = "auto",
       token = "xxxxxxxxx" # Your access key of hugging face
   )
+  # If you want to download a specific model of Gene-R1, using below code:
+  <!-- model_id = "ncbi/Gene-R1"
+  subfolder = "3B"
+  tokenizer_test = AutoTokenizer.from_pretrained(
+      model_id,
+      subfolder=subfolder,
+      token = "xxxxxxxxx" # Your access key of hugging face
+  )
+  model_test = AutoModelForCausalLM.from_pretrained(
+      model_id,
+      subfolder=subfolder,
+      device_map = "auto",
+      token = "xxxxxxxxx" # Your access key of hugging face
+  )-->
   def complete_chat(system, prompt, model, tokenizer):
       model.generation_config.do_sample=False
 More details of model usage can be referred at our GitHub: [GitHub](https://github.com/ncbi-nlp/Gene-R1)
+# Download statistics
+Hugging Face tracks downloads automatically based on requests to model query files such as `config.json`.
+To ensure downloads are counted, please load the full models directly from the Hub using `transformers`:
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+model_id = "ncbi/Gene-R1"
+tokenizer = AutoTokenizer.from_pretrained(model_id, hf_token)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", hf_token)
+```
 # Acknowledgments
 This research was supported in part by the Intramural Research Program of the National Institutes of Health (NIH).