Instructions to use nebius/EAGLE3-Llama-3.3-70B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nebius/EAGLE3-Llama-3.3-70B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="nebius/EAGLE3-Llama-3.3-70B-Instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nebius/EAGLE3-Llama-3.3-70B-Instruct")
model = AutoModelForCausalLM.from_pretrained("nebius/EAGLE3-Llama-3.3-70B-Instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nebius/EAGLE3-Llama-3.3-70B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nebius/EAGLE3-Llama-3.3-70B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nebius/EAGLE3-Llama-3.3-70B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nebius/EAGLE3-Llama-3.3-70B-Instruct

SGLang

How to use nebius/EAGLE3-Llama-3.3-70B-Instruct 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 "nebius/EAGLE3-Llama-3.3-70B-Instruct" \
    --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": "nebius/EAGLE3-Llama-3.3-70B-Instruct",
		"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 "nebius/EAGLE3-Llama-3.3-70B-Instruct" \
        --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": "nebius/EAGLE3-Llama-3.3-70B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nebius/EAGLE3-Llama-3.3-70B-Instruct with Docker Model Runner:
```
docker model run hf.co/nebius/EAGLE3-Llama-3.3-70B-Instruct
```

astrlrd commited on Feb 2

Commit

6ab4cf7

verified ·

1 Parent(s): 35f341d

Upload model weights

Browse files

Files changed (2) hide show

config.json +25 -0
model.safetensors +3 -0

config.json ADDED Viewed

	@@ -0,0 +1,25 @@

+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "model_type": "llama",
+    "num_hidden_layers": 1,
+    "use_custom_architecture": false,
+    "vocab_size": 128256,
+    "draft_vocab_size": 32000,
+    "bos_token_id": 128000,
+    "eos_token_id": 128001,
+    "hidden_act": "silu",
+    "hidden_size": 8192,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 131072,
+    "num_attention_heads": 64,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-05,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "use_cache": true,
+    "transformers_version": "4.47.0.dev0"
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:ec317982cd8637d1ae4a9301fc3b831a2fa86d496476e4364cc39e8e02a1eaae
+size 2806697464