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 / README.md

Voyager466920

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

d332a62 verified about 1 month ago

preview code

Raw

History Blame Contribute Delete

2.79 kB

	---
	tags:
	- text-generation
	- causal-lm
	- mixture-of-experts
	- custom-code
	- conversational
	- instruction-tuned
	language:
	- en
	pipeline_tag: text-generation
	library_name: transformers
	base_model: Voyager466920/Raptor
	---

	# Raptor

	Raptor is a 1.027B-parameter decoder-only causal language model with approximately 404M active parameters per token. It uses multi-head latent attention and six SwiGLU experts per layer with top-2 routing.

	This revision contains the English instruction-tuned checkpoint. It was initialized from the Raptor step-35,000 pretrained checkpoint and supervised fine-tuned for one epoch on a curated SmolTalk mixture. The retained checkpoint is SFT step 7,500, selected by validation loss.

	## Architecture

	- 18 layers
	- hidden size 1,024
	- latent attention dimension 256
	- 16 attention heads
	- six experts per layer, top-2 routing
	- expert hidden size 2,816
	- context length 2,048
	- 35,000-token SentencePiece vocabulary
	- 1.027B total parameters, about 404M active per token

	## Fine-tuning

	- Base checkpoint: pretraining step 35,000
	- Training examples: 511,721
	- Validation examples: 2,000
	- SFT epochs: 1
	- Best checkpoint: step 7,500
	- Best validation loss: 1.0597
	- Best validation perplexity: 2.8855
	- Training format: assistant-only loss over `### User:` and `### Assistant:` conversations

	## Usage

	The architecture and tokenizer use custom code, so loading requires `trust_remote_code=True`.

	```python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_id = "Voyager466920/Raptor"
	tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	trust_remote_code=True,
	torch_dtype=torch.bfloat16,
	device_map="auto",
	)

	messages = [{"role": "user", "content": "What is the capital of France?"}]
	inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	return_tensors="pt",
	).to(model.device)
	output = model.generate(
	inputs,
	max_new_tokens=128,
	do_sample=True,
	temperature=0.7,
	top_p=0.9,
	)
	print(tokenizer.decode(output[0, inputs.shape[1]:], skip_special_tokens=True))
	```

	## Limitations

	- This is an experimental 1B-scale model and may fail simple reasoning or arithmetic tasks.
	- Multi-turn memory and role consistency are unreliable.
	- Responses may become verbose, repetitive, inaccurate, biased, or unsafe.
	- The model is English-focused. The tokenizer has poor Korean coverage and maps many Korean words to the unknown token.
	- The architecture currently recomputes the full prefix during generation and does not implement a KV cache.

	## License

	No model license has been selected yet. Public availability does not grant additional usage rights beyond applicable law.