Instructions to use allenai/Flex-code-2x7B-1T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/Flex-code-2x7B-1T with Transformers:

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

pipe = pipeline("text-generation", model="allenai/Flex-code-2x7B-1T")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allenai/Flex-code-2x7B-1T")
model = AutoModelForCausalLM.from_pretrained("allenai/Flex-code-2x7B-1T", device_map="auto")
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 Settings

vLLM

How to use allenai/Flex-code-2x7B-1T with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/Flex-code-2x7B-1T"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "allenai/Flex-code-2x7B-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allenai/Flex-code-2x7B-1T

SGLang

How to use allenai/Flex-code-2x7B-1T 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 "allenai/Flex-code-2x7B-1T" \
    --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": "allenai/Flex-code-2x7B-1T",
		"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 "allenai/Flex-code-2x7B-1T" \
        --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": "allenai/Flex-code-2x7B-1T",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allenai/Flex-code-2x7B-1T with Docker Model Runner:
```
docker model run hf.co/allenai/Flex-code-2x7B-1T
```

shanearora commited on Oct 9, 2025

Commit

c58f920

verified ·

1 Parent(s): c9c2937

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -5

README.md CHANGED Viewed

@@ -28,16 +28,17 @@ This information and more can also be found:
 # Use
-Install `transformers` **from [this source](https://github.com/swj0419/transformers_flexolmo)** and run:
 ```python
-from transformers import Olmoe2ForCausalLM, AutoTokenizer
 import torch
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
-MODEL_NAME = "allenai/FlexOlmo-7x7B-1T"
-model = Olmoe2ForCausalLM.from_pretrained(MODEL_NAME).to(DEVICE)
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 inputs = tokenizer("Bitcoin is", return_tensors="pt")
 inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
 out = model.generate(**inputs, max_length=64)

 # Use
+Install `transformers` with version `4.57.0` or newer and run:
 ```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+MODEL_NAME = "allenai/Flex-code-2x7B-1T"
+TOKENIZER_NAME = "allenai/dolma2-tokenizer"
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME).to(DEVICE)
+tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_NAME)
 inputs = tokenizer("Bitcoin is", return_tensors="pt")
 inputs = {k: v.to(DEVICE) for k, v in inputs.items()}
 out = model.generate(**inputs, max_length=64)