Visual Question Answering
Transformers
Safetensors
PyTorch
English
tinyllava
text-generation
vision-language
custom_code
Eval Results (legacy)
Instructions to use keeeeenw/MicroLlava-Qwen3-0.6B-base-siglip2-so400m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use keeeeenw/MicroLlava-Qwen3-0.6B-base-siglip2-so400m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="keeeeenw/MicroLlava-Qwen3-0.6B-base-siglip2-so400m", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("keeeeenw/MicroLlava-Qwen3-0.6B-base-siglip2-so400m", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "TinyLlavaForConditionalGeneration" | |
| ], | |
| "cache_dir": null, | |
| "connector_type": "mlp2x_gelu", | |
| "hidden_size": 1024, | |
| "ignore_index": -100, | |
| "image_aspect_ratio": "square", | |
| "image_token_index": -200, | |
| "llm_model_name_or_path": "Qwen/Qwen3-0.6B-base", | |
| "model_type": "tinyllava", | |
| "auto_map": { | |
| "AutoConfig": "configuration.TinyLlavaConfig", | |
| "AutoModelForCausalLM": "modeling_tinyllava_qwen3.TinyLlavaForConditionalGeneration" | |
| }, | |
| "num_queries": 128, | |
| "num_resampler_layers": 3, | |
| "pad_token": "<|endoftext|>", | |
| "pad_token_id": 151643, | |
| "resampler_hidden_size": 768, | |
| "text_config": { | |
| "_name_or_path": "Qwen/Qwen3-0.6B-base", | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "tokenizer_model_max_length": 2048, | |
| "tokenizer_name_or_path": "Qwen/Qwen3-0.6B-base", | |
| "tokenizer_padding_side": "right", | |
| "tokenizer_use_fast": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.55.2", | |
| "tune_type_connector": "full", | |
| "tune_type_llm": "full", | |
| "tune_type_vision_tower": "frozen", | |
| "tune_vision_tower_from_layer": 0, | |
| "use_cache": true, | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 384, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_name_or_path": "google/siglip2-so400m-patch14-384", | |
| "model_name_or_path2": "", | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14 | |
| }, | |
| "vision_feature_layer": -2, | |
| "vision_feature_select_strategy": "patch", | |
| "vision_hidden_size": 1152, | |
| "vision_model_name_or_path": "google/siglip2-so400m-patch14-384", | |
| "vision_model_name_or_path2": "", | |
| "vocab_size": 151936 | |
| } | |