Instructions to use kyutai/CASA-Helium1-VL-2B-Shared with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kyutai/CASA-Helium1-VL-2B-Shared with Transformers:

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

pipe = pipeline("image-text-to-text", model="kyutai/CASA-Helium1-VL-2B-Shared", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kyutai/CASA-Helium1-VL-2B-Shared", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use kyutai/CASA-Helium1-VL-2B-Shared with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kyutai/CASA-Helium1-VL-2B-Shared"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kyutai/CASA-Helium1-VL-2B-Shared",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kyutai/CASA-Helium1-VL-2B-Shared

SGLang

How to use kyutai/CASA-Helium1-VL-2B-Shared 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 "kyutai/CASA-Helium1-VL-2B-Shared" \
    --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": "kyutai/CASA-Helium1-VL-2B-Shared",
		"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 "kyutai/CASA-Helium1-VL-2B-Shared" \
        --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": "kyutai/CASA-Helium1-VL-2B-Shared",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kyutai/CASA-Helium1-VL-2B-Shared with Docker Model Runner:
```
docker model run hf.co/kyutai/CASA-Helium1-VL-2B-Shared
```

CASA-Helium1-VL-2B-Shared / config.json

ameroyer

Super-squash branch 'main' using huggingface_hub

080b2ba 2 months ago

Raw History Blame Contribute Delete

1.69 kB

{
  "architectures": [
    "V2Helium1"
  ],
  "auto_map": {
    "AutoConfig": "configuration_helium1_ca.Helium1CAConfig",
    "AutoModel": "modeling_helium1_ca.V2Helium1"
  },
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "cross_attention": true,
  "eos_token_id": null,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 8192,
  "max_position_embeddings": 4096,
  "mlp_bias": false,
  "model_type": "helium1_ca",
  "num_attention_heads": 16,
  "num_hidden_layers": 28,
  "num_key_value_heads": 8,
  "pad_token_id": 3,
  "post_image_tokens": [
    5
  ],
  "pre_image_tokens": [
    4
  ],
  "pretraining_tp": 1,
  "rms_norm_eps": 1e-08,
  "rope_scaling": null,
  "rope_theta": 20000.0,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "vision_config": {
    "depth": 32,
    "fullatt_block_indexes": [
      7,
      15,
      23,
      31
    ],
    "hidden_act": "silu",
    "hidden_size": 1280,
    "image_mean": [
      0.48145466,
      0.4578275,
      0.40821073
    ],
    "image_std": [
      0.26862954,
      0.26130258,
      0.27577711
    ],
    "in_channels": 3,
    "in_chans": 3,
    "intermediate_size": 3420,
    "model_type": "qwen2_5_vl",
    "num_heads": 16,
    "out_dim": 2048,
    "out_hidden_size": 2048,
    "patch_size": 14,
    "spatial_merge_size": 2,
    "spatial_patch_size": 14,
    "temporal_patch_size": 1,
    "tokens_per_second": 2,
    "window_size": 112
  },
  "vocab_size": 64000,
  "xa_custom_norm": true,
  "xa_layers": [],
  "image_proj_norm": false,
  "xa_share_qkvo": true
}

	{
	"architectures": [
	"V2Helium1"
	],
	"auto_map": {
	"AutoConfig": "configuration_helium1_ca.Helium1CAConfig",
	"AutoModel": "modeling_helium1_ca.V2Helium1"
	},
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"cross_attention": true,
	"eos_token_id": null,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 8192,
	"max_position_embeddings": 4096,
	"mlp_bias": false,
	"model_type": "helium1_ca",
	"num_attention_heads": 16,
	"num_hidden_layers": 28,
	"num_key_value_heads": 8,
	"pad_token_id": 3,
	"post_image_tokens": [
	5
	],
	"pre_image_tokens": [
	4
	],
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-08,
	"rope_scaling": null,
	"rope_theta": 20000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.51.3",
	"use_cache": true,
	"vision_config": {
	"depth": 32,
	"fullatt_block_indexes": [
	7,
	15,
	23,
	31
	],
	"hidden_act": "silu",
	"hidden_size": 1280,
	"image_mean": [
	0.48145466,
	0.4578275,
	0.40821073
	],
	"image_std": [
	0.26862954,
	0.26130258,
	0.27577711
	],
	"in_channels": 3,
	"in_chans": 3,
	"intermediate_size": 3420,
	"model_type": "qwen2_5_vl",
	"num_heads": 16,
	"out_dim": 2048,
	"out_hidden_size": 2048,
	"patch_size": 14,
	"spatial_merge_size": 2,
	"spatial_patch_size": 14,
	"temporal_patch_size": 1,
	"tokens_per_second": 2,
	"window_size": 112
	},
	"vocab_size": 64000,
	"xa_custom_norm": true,
	"xa_layers": [],
	"image_proj_norm": false,
	"xa_share_qkvo": true
	}