Instructions to use Voyager466920/Raptor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Voyager466920/Raptor with Transformers:

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

pipe = pipeline("text-generation", model="Voyager466920/Raptor", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Voyager466920/Raptor", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Voyager466920/Raptor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Voyager466920/Raptor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Voyager466920/Raptor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Voyager466920/Raptor

SGLang

How to use Voyager466920/Raptor 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 "Voyager466920/Raptor" \
    --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": "Voyager466920/Raptor",
		"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 "Voyager466920/Raptor" \
        --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": "Voyager466920/Raptor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Voyager466920/Raptor with Docker Model Runner:
```
docker model run hf.co/Voyager466920/Raptor
```

Raptor / config.json

Voyager466920

Update Raptor with SmolTalk instruction-tuned checkpoint at SFT step 7500

d332a62 verified about 1 month ago

Raw

History Blame Contribute Delete

762 Bytes

	{
	"architectures": [
	"RaptorForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_raptor.RaptorConfig",
	"AutoModelForCausalLM": "modeling_raptor.RaptorForCausalLM"
	},
	"bos_token_id": 2,
	"dim": 1024,
	"dtype": "bfloat16",
	"eos_token_id": 3,
	"expert_hidden_dim": 2816,
	"gradient_checkpointing": false,
	"hidden_size": 1024,
	"latent_dim": 256,
	"load_balance_weight": 0.01,
	"max_position_embeddings": 2048,
	"max_seq_len": 2048,
	"model_type": "raptor",
	"moe_top_k": 2,
	"num_attention_heads": 16,
	"num_experts": 6,
	"num_heads": 16,
	"num_hidden_layers": 18,
	"num_layers": 18,
	"pad_token_id": 0,
	"rope_theta": 10000.0,
	"router_z_weight": 0.001,
	"transformers_version": "4.57.6",
	"vocab_size": 35000
	}