|
{ |
|
"_name_or_path": "vilm/StableCapybara-VL", |
|
"architectures": [ |
|
"LlavaStableLMEpochForCausalLM" |
|
], |
|
"auto_map": { |
|
"AutoConfig": "vilm/StableCapybara--configuration_stablelm_epoch.StableLMEpochConfig", |
|
"AutoModelForCausalLM": "vilm/StableCapybara--modeling_stablelm_epoch.StableLMEpochForCausalLM" |
|
}, |
|
"bos_token_id": 0, |
|
"eos_token_id": 0, |
|
"freeze_mm_mlp_adapter": false, |
|
"hidden_act": "silu", |
|
"hidden_size": 2560, |
|
"image_aspect_ratio": "pad", |
|
"image_grid_pinpoints": null, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 6912, |
|
"max_position_embeddings": 4096, |
|
"mm_hidden_size": 1024, |
|
"mm_projector_type": "mlp2x_gelu", |
|
"mm_use_im_patch_token": false, |
|
"mm_use_im_start_end": false, |
|
"mm_vision_select_feature": "patch", |
|
"mm_vision_select_layer": -2, |
|
"mm_vision_tower": "openai/clip-vit-large-patch14-336", |
|
"model_type": "llava_stablelm_epoch", |
|
"norm_eps": 1e-05, |
|
"num_attention_heads": 32, |
|
"num_heads": 32, |
|
"num_hidden_layers": 32, |
|
"num_key_value_heads": 32, |
|
"rope_pct": 0.25, |
|
"rope_theta": 10000, |
|
"rotary_scaling_factor": 1.0, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.34.1", |
|
"tune_mm_mlp_adapter": false, |
|
"use_cache": true, |
|
"use_mm_proj": true, |
|
"vocab_size": 50304 |
|
} |
|
|