Instructions to use and-emili/aera-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use and-emili/aera-4b with Transformers:

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

pipe = pipeline("text-generation", model="and-emili/aera-4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("and-emili/aera-4b")
model = AutoModelForMultimodalLM.from_pretrained("and-emili/aera-4b")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use and-emili/aera-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "and-emili/aera-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "and-emili/aera-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/and-emili/aera-4b

SGLang

How to use and-emili/aera-4b 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 "and-emili/aera-4b" \
    --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": "and-emili/aera-4b",
		"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 "and-emili/aera-4b" \
        --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": "and-emili/aera-4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use and-emili/aera-4b with Docker Model Runner:
```
docker model run hf.co/and-emili/aera-4b
```

lorenzoiotti commited on Sep 18, 2025

Commit

5ca17e5

verified ·

1 Parent(s): 5762950

Update model weights - keeping existing tokenizer_config.json

Browse files

Files changed (4) hide show

config.json +40 -2
generation_config.json +3 -3
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1

config.json CHANGED Viewed

@@ -10,7 +10,45 @@
   "hidden_size": 2560,
   "initializer_range": 0.02,
   "intermediate_size": 9728,
-  "max_position_embeddings": 40960,
   "max_window_layers": 36,
   "model_type": "qwen3",
   "num_attention_heads": 32,
@@ -19,7 +57,7 @@
   "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 1000000,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",

   "hidden_size": 2560,
   "initializer_range": 0.02,
   "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
   "max_window_layers": 36,
   "model_type": "qwen3",
   "num_attention_heads": 32,
   "pad_token_id": 151654,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
+  "rope_theta": 5000000,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",

generation_config.json CHANGED Viewed

@@ -5,10 +5,10 @@
     151645,
     151643
   ],
-  "max_length": 40960,
   "pad_token_id": 151654,
-  "temperature": 0.6,
   "top_k": 20,
-  "top_p": 0.95,
   "transformers_version": "4.51.0"
 }

     151645,
     151643
   ],
+  "max_length": 262144,
   "pad_token_id": 151654,
+  "temperature": 0.7,
   "top_k": 20,
+  "top_p": 0.8,
   "transformers_version": "4.51.0"
 }

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff1908664eb5301d068ce389db18df16b862397da0cf9ba708077fcd99d355b0
 size 4967214624

 version https://git-lfs.github.com/spec/v1
+oid sha256:8f65530a5b1a76463aaf49bc5e920c98cded647e26613161d8d5393c985cdd72
 size 4967214624

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d13eb1fbc28800301c7450a790deb041fd89e718a7859b1ddc7f9bfdcbff8c9
 size 3077767360

 version https://git-lfs.github.com/spec/v1
+oid sha256:0b7212fba7cb864d59c9aa22670a2cd20f70ded1a756cc17b4379cfa424c04bf
 size 3077767360