Yi-VL-34B-safetensors / config.json
johannhartmann's picture
Upload folder using huggingface_hub
a80c363 verified
{
"_name_or_path": "./yi-vl-34b",
"architectures": [
"LlavaLlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 7168,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 20480,
"max_position_embeddings": 4096,
"mm_hidden_size": 1280,
"mm_projector_type": "mlp2x_gelu_Norm",
"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": "./vit/clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448",
"model_type": "llava",
"moe_layer": null,
"moe_mode": "easy",
"num_attention_heads": 56,
"num_hidden_layers": 60,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 5000000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.34.0",
"tune_mm_mlp_adapter": false,
"tune_vision_tower": true,
"use_cache": false,
"use_mm_proj": true,
"vocab_size": 64000
}