Instructions to use TrishanuDas/tayavision-alignment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TrishanuDas/tayavision-alignment with Transformers:

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

pipe = pipeline("image-text-to-text", model="TrishanuDas/tayavision-alignment")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("TrishanuDas/tayavision-alignment", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TrishanuDas/tayavision-alignment with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TrishanuDas/tayavision-alignment"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TrishanuDas/tayavision-alignment",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/TrishanuDas/tayavision-alignment

SGLang

How to use TrishanuDas/tayavision-alignment 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 "TrishanuDas/tayavision-alignment" \
    --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": "TrishanuDas/tayavision-alignment",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "TrishanuDas/tayavision-alignment" \
        --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": "TrishanuDas/tayavision-alignment",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use TrishanuDas/tayavision-alignment with Docker Model Runner:
```
docker model run hf.co/TrishanuDas/tayavision-alignment
```

tayavision-alignment / config.json

TrishanuDas

Upload TinyAyaVision (SigLIP + LoRA-merged instruct)

e163944 verified about 1 month ago

raw

history blame contribute delete

6.94 kB

	{
	"_text_config_obj": {
	"_name_or_path": "CohereLabs/tiny-aya-global",
	"_sliding_window_pattern": 4,
	"architectures": [
	"Cohere2ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 2,
	"cache_implementation": "hybrid",
	"chunk_size_feed_forward": 0,
	"dtype": "bfloat16",
	"eos_token_id": 3,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"intermediate_size": 11008,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"layer_norm_eps": 1e-05,
	"layer_switch": 4,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"logit_scale": 1.0,
	"max_position_embeddings": 500000,
	"model_type": "cohere2",
	"num_attention_heads": 16,
	"num_hidden_layers": 36,
	"num_key_value_heads": 4,
	"order_of_interleaved_layers": "local_attn_first",
	"output_attentions": false,
	"output_hidden_states": false,
	"pad_token_id": 0,
	"position_embedding_type": "rope_gptj",
	"problem_type": null,
	"return_dict": true,
	"rope_parameters": {
	"rope_theta": 50000,
	"rope_type": "default"
	},
	"rotary_pct": 1.0,
	"sliding_window": 4096,
	"sliding_window_pattern": 4,
	"tie_word_embeddings": true,
	"use_cache": true,
	"use_embedding_sharing": true,
	"use_gated_activation": true,
	"use_parallel_block": true,
	"use_parallel_embedding": false,
	"use_qk_norm": false,
	"vocab_size": 262144
	},
	"adapter_layer_norm_eps": 1e-06,
	"architectures": [
	"TinyAyaVisionForConditionalGeneration"
	],
	"cache_dir": null,
	"connector_intermediate_size": 2048,
	"connector_type": "pixel_shuffle",
	"downsample_factor": 2,
	"dtype": "bfloat16",
	"image_size": 384,
	"image_token": "<image>",
	"image_token_id": 261010,
	"in_token_limit": 1024,
	"llm_hidden_size": 2048,
	"llm_model_name": "CohereLabs/tiny-aya-global",
	"llm_vocab_size": 262144,
	"model_type": "tiny_aya_vision",
	"num_llm_layers": 36,
	"num_tokens_after_shuffle": 196,
	"num_vision_tokens": 729,
	"padded_grid_size": 28,
	"patch_size": 14,
	"pixel_shuffle_embed_dim": 4608,
	"post_projector_rms_norm": false,
	"text_config": {
	"_name_or_path": "CohereLabs/tiny-aya-global",
	"_sliding_window_pattern": 4,
	"architectures": [
	"Cohere2ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 2,
	"cache_implementation": "hybrid",
	"chunk_size_feed_forward": 0,
	"dtype": "bfloat16",
	"eos_token_id": 3,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 2048,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"intermediate_size": 11008,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"layer_norm_eps": 1e-05,
	"layer_switch": 4,
	"layer_types": [
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention"
	],
	"logit_scale": 1.0,
	"max_position_embeddings": 500000,
	"model_type": "cohere2",
	"num_attention_heads": 16,
	"num_hidden_layers": 36,
	"num_key_value_heads": 4,
	"order_of_interleaved_layers": "local_attn_first",
	"output_attentions": false,
	"output_hidden_states": false,
	"pad_token_id": 0,
	"position_embedding_type": "rope_gptj",
	"problem_type": null,
	"return_dict": true,
	"rope_parameters": {
	"rope_theta": 50000,
	"rope_type": "default"
	},
	"rotary_pct": 1.0,
	"sliding_window": 4096,
	"sliding_window_pattern": 4,
	"tie_word_embeddings": true,
	"transformers_version": "5.5.3",
	"use_cache": true,
	"use_embedding_sharing": true,
	"use_gated_activation": true,
	"use_parallel_block": true,
	"use_parallel_embedding": false,
	"use_qk_norm": false,
	"vocab_size": 262144
	},
	"tokens_per_tile": 4,
	"transformers_version": "5.5.3",
	"trust_remote_code": false,
	"vision_encoder_type": "siglip",
	"vision_feature_layer": -1,
	"vision_feature_select_strategy": "full",
	"vision_grid_size": 27,
	"vision_hidden_size": 1152,
	"vision_model_name": "google/siglip2-so400m-patch14-384",
	"vision_tower_config": {
	"_name_or_path": "google/siglip2-so400m-patch14-384",
	"architectures": null,
	"attention_dropout": 0.0,
	"chunk_size_feed_forward": 0,
	"dtype": "bfloat16",
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"image_size": 384,
	"intermediate_size": 4304,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"layer_norm_eps": 1e-06,
	"model_type": "siglip_vision_model",
	"num_attention_heads": 16,
	"num_channels": 3,
	"num_hidden_layers": 27,
	"output_attentions": false,
	"output_hidden_states": false,
	"patch_size": 14,
	"problem_type": null,
	"return_dict": true,
	"transformers_version": "5.5.3"
	}
	}