SVE-Math-Qwen2.5-7B / config.json
Shan Zhang
initial commit
ce30a51
{
"_name_or_path": "./checkpoints_mwq/llava1.5_7b_Qwen2.5_qa_tune_+all",
"architectures": [
"LlavaQwenForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 3584,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 4096,
"max_window_layers": 28,
"merge_version": "identify_channel",
"mm_hidden_size": 1024,
"mm_projector_lr": 3e-05,
"mm_projector_type": "mlp2x_gelu",
"mm_resampler_type": null,
"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_qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"num_of_kvs": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 2048,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"use_sliding_window": false,
"vocab_size": 152064
}