|
{ |
|
"model_type": "llama", |
|
"architectures": ["MultimodalLFM2Model"], |
|
|
|
"_name_or_path": "GoofyLM/N2.2-Eye-1.3B", |
|
"auto_map": { |
|
"AutoModelForCausalLM": "modeling_n2_eye.MultimodalLFM2Model", |
|
"AutoConfig": "modeling_n2_eye.MultimodalLFM2Config" |
|
}, |
|
|
|
"lfm2_model_name": "LiquidAI/LFM2-1.2B", |
|
"clip_model_name": "openai/clip-vit-base-patch32", |
|
"vision_projection_dim": 512, |
|
|
|
"language_model_config": { |
|
"model_type": "lfm2", |
|
"hidden_size": 1536, |
|
"vocab_size": 50257, |
|
"max_position_embeddings": 2048 |
|
}, |
|
|
|
"vision_encoder_config": { |
|
"model_type": "clip_vision_model", |
|
"hidden_size": 768 |
|
}, |
|
|
|
"projection_config": { |
|
"vision_hidden_size": 768, |
|
"vision_projection_dim": 512, |
|
"language_hidden_size": 1536, |
|
"dropout": 0.1 |
|
}, |
|
|
|
"image_token": "<image>", |
|
"max_length": 2048, |
|
|
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.46.0", |
|
"use_cache": true, |
|
|
|
"chat_template": "{% set system_message = 'You are a helpful assistant trained by Liquid AI. You can see and understand images.' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}<|im_start|>system\n{{ system_message }}<|im_end|>\n<image>\n{% for message in loop_messages %}<|im_start|>{{ message['role'] }}\n{{ message['content'] }}<|im_end|>\n{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}" |
|
} |