maya_full_ft / config.json
nahidalam's picture
Track .safetensors files with LFS
d499056
raw
history blame
1.21 kB
{
"_name_or_path": "CohereForAI/aya-23-8B",
"architectures": [
"LlavaCohereForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 5,
"eos_token_id": 255001,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 14336,
"layer_norm_eps": 1e-05,
"logit_scale": 0.0625,
"max_position_embeddings": 8192,
"mm_hidden_size": 768,
"mm_patch_merge_type": "flat",
"mm_projector_lr": null,
"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": "google/siglip-base-patch16-256-multilingual",
"model_type": "llava_cohere",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": 0,
"rope_theta": 10000,
"tokenizer_model_max_length": 2048,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.42.3",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"use_qk_norm": false,
"vocab_size": 256000
}