Instructions to use manycore-research/SpatialLM1.1-Llama-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use manycore-research/SpatialLM1.1-Llama-1B with Transformers:

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

pipe = pipeline("text-generation", model="manycore-research/SpatialLM1.1-Llama-1B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("manycore-research/SpatialLM1.1-Llama-1B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use manycore-research/SpatialLM1.1-Llama-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "manycore-research/SpatialLM1.1-Llama-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "manycore-research/SpatialLM1.1-Llama-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/manycore-research/SpatialLM1.1-Llama-1B

SGLang

How to use manycore-research/SpatialLM1.1-Llama-1B 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 "manycore-research/SpatialLM1.1-Llama-1B" \
    --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": "manycore-research/SpatialLM1.1-Llama-1B",
		"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 "manycore-research/SpatialLM1.1-Llama-1B" \
        --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": "manycore-research/SpatialLM1.1-Llama-1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use manycore-research/SpatialLM1.1-Llama-1B with Docker Model Runner:
```
docker model run hf.co/manycore-research/SpatialLM1.1-Llama-1B
```

SpatialLM1.1-Llama-1B / config.json

ysmao

Initial commit

7d94285 about 1 year ago

Raw

History Blame Contribute Delete

1.64 kB

	{
	"architectures": [
	"SpatialLMLlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 128000,
	"eos_token_id": [
	128001,
	128008,
	128009
	],
	"head_dim": 64,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 8192,
	"max_position_embeddings": 131072,
	"mlp_bias": false,
	"model_type": "spatiallm_llama",
	"num_attention_heads": 32,
	"num_hidden_layers": 16,
	"num_key_value_heads": 8,
	"point_backbone": "sonata",
	"point_config": {
	"enc_channels": [
	48,
	96,
	192,
	384,
	512
	],
	"enc_depths": [
	3,
	3,
	3,
	12,
	3
	],
	"enc_mode": true,
	"enc_num_head": [
	3,
	6,
	12,
	24,
	32
	],
	"enc_patch_size": [
	1024,
	1024,
	1024,
	1024,
	1024
	],
	"in_channels": 6,
	"mask_token": true,
	"mlp_ratio": 4,
	"order": [
	"z",
	"z-trans",
	"hilbert",
	"hilbert-trans"
	],
	"stride": [
	2,
	2,
	2,
	2
	],
	"num_bins": 1280
	},
	"projector": "mlp",
	"point_end_token_id": 128012,
	"point_start_token_id": 128011,
	"point_token_id": 128013,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"factor": 32.0,
	"high_freq_factor": 4.0,
	"low_freq_factor": 1.0,
	"original_max_position_embeddings": 8192,
	"rope_type": "llama3"
	},
	"rope_theta": 500000.0,
	"tie_word_embeddings": true,
	"torch_dtype": "float32",
	"transformers_version": "4.46.1",
	"use_cache": false,
	"vocab_size": 128256
	}