config.json

{
 "_name_or_path": "checkpoints/mistral-nemo-instruct",
 "architectures": [
 "LlavaMistralForCausalLM"
 ],
 "attention_bias": false,
 "attention_dropout": 0.0,
 "bos_token_id": 1,
 "eos_token_id": 2,
 "freeze_mm_mlp_adapter": false,
 "head_dim": 128,
 "hidden_act": "silu",
 "hidden_size": 5120,
 "image_aspect_ratio": "pad",
 "initializer_range": 0.02,
 "intermediate_size": 14336,
 "max_position_embeddings": 1024000,
 "mlp_bias": false,
 "mm_hidden_size": 2048,
 "mm_patch_merge_type": "flat",
 "mm_projector_lr": 7e-06,
 "mm_projector_type": "glu",
 "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": "checkpoints/ve-ft-mine-4e-v2.0",
 "model_type": "llava_llama",
 "new_img_size": null,
 "num_attention_heads": 32,
 "num_hidden_layers": 40,
 "num_key_value_heads": 8,
 "pretraining_tp": 1,
 "rms_norm_eps": 1e-05,
 "rope_scaling": null,
 "rope_theta": 1000000.0,
 "s2": false,
 "s2_max_split_size": 384,
 "s2_scales": "384,768",
 "sliding_window": null,
 "tie_word_embeddings": false,
 "tokenizer_model_max_length": 2048,
 "tokenizer_padding_side": "right",
 "torch_dtype": "float16",
 "transformers_version": "4.43.0.dev0",
 "tune_mm_mlp_adapter": false,
 "unfreeze_mm_vision_tower": true,
 "use_cache": true,
 "use_mm_proj": true,
 "video_fps": 1,
 "video_frames_num": 16,
 "vision_config": {
 "_name_or_path": "",
 "add_cross_attention": false,
 "architectures": null,
 "bad_words_ids": null,
 "begin_suppress_tokens": null,
 "bos_token_id": null,
 "chunk_size_feed_forward": 0,
 "cross_attention_hidden_size": null,
 "decoder_start_token_id": null,
 "depths": [
 1,
 1,
 9,
 1
 ],
 "dim_embed": [
 256,
 512,
 1024,
 2048
 ],
 "diversity_penalty": 0.0,
 "do_sample": false,
 "drop_path_rate": 0.1,
 "early_stopping": false,
 "enable_checkpoint": false,
 "encoder_no_repeat_ngram_size": 0,
 "eos_token_id": null,
 "exponential_decay_length_penalty": null,
 "finetuning_task": null,
 "forced_bos_token_id": null,
 "forced_eos_token_id": null,
 "id2label": {
 "0": "LABEL_0",
 "1": "LABEL_1"
 },
 "image_feature_source": [
 "spatial_avg_pool",
 "temporal_avg_pool"
 ],
 "image_pos_embed": {
 "max_pos_embeddings": 50,
 "type": "learned_abs_2d"
 },
 "is_decoder": false,
 "is_encoder_decoder": false,
 "label2id": {
 "LABEL_0": 0,
 "LABEL_1": 1
 },
 "length_penalty": 1.0,
 "max_length": 20,
 "min_length": 0,
 "model_type": "",
 "no_repeat_ngram_size": 0,
 "num_beam_groups": 1,
 "num_beams": 1,
 "num_groups": [
 8,
 16,
 32,
 64
 ],
 "num_heads": [
 8,
 16,
 32,
 64
 ],
 "num_return_sequences": 1,
 "output_attentions": false,
 "output_hidden_states": false,
 "output_scores": false,
 "pad_token_id": null,
 "patch_padding": [
 3,
 1,
 1,
 1
 ],
 "patch_prenorm": [
 false,
 true,
 true,
 true
 ],
 "patch_size": [
 7,
 3,
 3,
 3
 ],
 "patch_stride": [
 4,
 2,
 2,
 2
 ],
 "prefix": null,
 "problem_type": null,
 "projection_dim": 1024,
 "pruned_heads": {},
 "remove_invalid_values": false,
 "repetition_penalty": 1.0,
 "return_dict": true,
 "return_dict_in_generate": false,
 "sep_token_id": null,
 "suppress_tokens": null,
 "task_specific_params": null,
 "temperature": 1.0,
 "tf_legacy_loss": false,
 "tie_encoder_decoder": false,
 "tie_word_embeddings": true,
 "tokenizer_class": null,
 "top_k": 50,
 "top_p": 1.0,
 "torch_dtype": null,
 "torchscript": false,
 "typical_p": 1.0,
 "use_bfloat16": false,
 "visual_temporal_embedding": {
 "max_temporal_embeddings": 100,
 "type": "COSINE"
 },
 "window_size": 12
 },
 "vocab_size": 131072
}