Instructions to use thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509 with Transformers:

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

pipe = pipeline("text-generation", model="thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509")

# Load model directly
from transformers import AutoTokenizer, LlamaForCausalLMEagle3

tokenizer = AutoTokenizer.from_pretrained("thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509")
model = LlamaForCausalLMEagle3.from_pretrained("thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509

SGLang

How to use thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509 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 "thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509" \
    --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": "thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509",
		"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 "thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509" \
        --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": "thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509 with Docker Model Runner:
```
docker model run hf.co/thomaskiefer/EAGLE3-Apertus-8B-Instruct-2509
```

thomaskiefer commited on Nov 30, 2025

Commit

e52b8ea

verified ·

1 Parent(s): 824e733

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

config.json +31 -0
model.safetensors +3 -0
training_state.pt +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,31 @@

+{
+  "architectures": [
+    "LlamaForCausalLMEagle3"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "draft_vocab_size": 32000,
+  "dtype": "bfloat16",
+  "eos_token_id": 68,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 21504,
+  "max_position_embeddings": 65536,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 8,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 131072
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d734ceedbc402b2a927e9eeef3962053be24a68f0b04970eb8e62cdd5580d347
+size 1025928688

training_state.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:ca40d44acda4b26792182048f06c4be392a0cea08ab9c382b1f66d1b6ec7d799
+size 4119