Image-Text-to-Text
Transformers
Safetensors
GGUF
English
qwen2_5_vl
remyx
qwen2.5-vl
spatial-reasoning
multimodal
vlm
vqasynth
thinking
reasoning
test-time-compute
robotics
embodied-ai
quantitative-spatial-reasoning
distance-estimation
visual-question-answering
conversational
Eval Results
text-generation-inference
{ | |
"alpha_pattern": {}, | |
"auto_mapping": null, | |
"base_model_name_or_path": "UCSC-VLAA/VLAA-Thinker-Qwen2.5VL-3B", | |
"bias": "none", | |
"fan_in_fan_out": false, | |
"inference_mode": true, | |
"init_lora_weights": true, | |
"layer_replication": null, | |
"layers_pattern": null, | |
"layers_to_transform": null, | |
"loftq_config": {}, | |
"lora_alpha": 256, | |
"lora_dropout": 0.05, | |
"megatron_config": null, | |
"megatron_core": "megatron.core", | |
"modules_to_save": null, | |
"peft_type": "LORA", | |
"r": 128, | |
"rank_pattern": {}, | |
"revision": null, | |
"target_modules": [ | |
"v_proj", | |
"q_proj" | |
], | |
"task_type": "CAUSAL_LM", | |
"use_dora": false, | |
"use_rslora": false | |
} |