Instructions to use allenai/Olmo-3-7B-RL-Zero-General with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use allenai/Olmo-3-7B-RL-Zero-General with Transformers:

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

pipe = pipeline("text-generation", model="allenai/Olmo-3-7B-RL-Zero-General")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-7B-RL-Zero-General")
model = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-RL-Zero-General")
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/Olmo-3-7B-RL-Zero-General with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "allenai/Olmo-3-7B-RL-Zero-General"
# 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/Olmo-3-7B-RL-Zero-General",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/allenai/Olmo-3-7B-RL-Zero-General

SGLang

How to use allenai/Olmo-3-7B-RL-Zero-General 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/Olmo-3-7B-RL-Zero-General" \
    --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/Olmo-3-7B-RL-Zero-General",
		"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/Olmo-3-7B-RL-Zero-General" \
        --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/Olmo-3-7B-RL-Zero-General",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use allenai/Olmo-3-7B-RL-Zero-General with Docker Model Runner:
```
docker model run hf.co/allenai/Olmo-3-7B-RL-Zero-General
```

saurabh5 commited on Nov 18, 2025

Commit

58170b1

verified ·

1 Parent(s): 0a02a23

Update config.json on branch main

Browse files

Files changed (1) hide show

config.json +6 -5

config.json CHANGED Viewed

@@ -1,9 +1,10 @@
 {
   "architectures": [
-    "Olmo2RetrofitForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "eos_token_id": 100257,
   "hidden_act": "silu",
   "hidden_size": 4096,
@@ -44,7 +45,7 @@
     "full_attention"
   ],
   "max_position_embeddings": 65536,
-  "model_type": "olmo2-retrofit",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
@@ -61,8 +62,8 @@
   "rope_theta": 500000,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.54.0.dev0",
-  "use_cache": false,
   "vocab_size": 100278
 }

 {
   "architectures": [
+    "Olmo3ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "dtype": "bfloat16",
   "eos_token_id": 100257,
   "hidden_act": "silu",
   "hidden_size": 4096,
     "full_attention"
   ],
   "max_position_embeddings": 65536,
+  "model_type": "olmo3",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "rope_theta": 500000,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
   "vocab_size": 100278
 }