Visual Question Answering
Transformers
English
videollama2_mixtral
text-generation
multimodal large language model
large video-language model
Inference Endpoints
VideoLLaMA2-8x7B-Base / config.json
ClownRat's picture
Update config.json
bab71d8 verified
{
"_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"architectures": [
"MixtralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "square",
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"mm_hidden_size": 1024,
"mm_projector_lr": null,
"mm_projector_type": "stc_connector",
"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": "videollama2_mixtral",
"num_attention_heads": 32,
"num_experts_per_tok": 2,
"num_frames": 8,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"num_local_experts": 8,
"output_router_logits": false,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"router_aux_loss_coef": 0.02,
"sliding_window": null,
"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": true,
"use_cache": false,
"use_mm_proj": true,
"vocab_size": 32000
}