LESA / config.json
HZXC's picture
Upload LESA model weights
5655cd9 verified
Raw History Blame Contribute Delete
2.06 kB
{
"_commit_hash": null,
"architectures": [
"LESAChatModel"
],
"downsample_ratio": 0.5,
"dynamic_image_size": true,
"force_image_size": 448,
"hidden_size": 4096,
"llm_config": {
"_name_or_path": "internlm/internlm2_5-7b-chat",
"architectures": [
"InternLM2ForCausalLM"
],
"attn_implementation": "flash_attention_2",
"bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "internlm2",
"num_key_value_heads": 8,
"pad_token_id": 2,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 2.0,
"type": "dynamic"
},
"rope_theta": 1000000,
"torch_dtype": "bfloat16",
"use_bfloat16": true,
"vocab_size": 92561
},
"max_dynamic_patch": 12,
"memory_limits": [
6,
4,
4,
1
],
"memory_tokens_per_slot": 32,
"min_dynamic_patch": 1,
"min_trigger_interval": 3,
"model_type": "sa2va_chat",
"pad2square": false,
"presence_off_threshold": 0.4,
"presence_on_threshold": 0.5,
"ps_version": "v2",
"select_layer": -1,
"template": "qwen_chat",
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": null,
"trigger_threshold": 0.4,
"use_backbone_lora": 0,
"use_llm_lora": 0,
"use_thumbnail": true,
"video_memory_hidden_dim": 512,
"vision_config": {
"architectures": [
"InternVisionModel"
],
"attention_dropout": 0.0,
"drop_path_rate": 0.0,
"dropout": 0.0,
"hidden_act": "gelu",
"hidden_size": 1024,
"image_size": 448,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-06,
"model_type": "intern_vit_6b",
"norm_type": "layer_norm",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 24,
"qk_normalization": false,
"qkv_bias": true,
"torch_dtype": "bfloat16",
"use_bfloat16": true,
"use_flash_attn": true
},
"lookback_frames": 8
}