Instructions to use manycore-research/SpatialLM1.1-Llama-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
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
File size: 1,636 Bytes
7d94285 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | {
"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
} |