ALLaVA-StableLM2-1_6B / config.json
g-h-chen's picture
upload config.json
57e3690 verified
raw
history blame
1.36 kB
{
"_name_or_path": "FreedomIntelligence/ALLaVA-StableLM2-1_6B",
"architectures": [
"LlavaStableLM_1_6bForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
"AutoModelForCausalLM": "modeling_llava_stablelm_1_6b.LlavaStableLM_1_6bForCausalLM"
},
"bos_token_id": 100257,
"eos_token_id": 100257,
"hidden_act": "silu",
"hidden_size": 2048,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 4096,
"mm_hidden_size": 1024,
"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": "openai/clip-vit-large-patch14-336",
"model_type": "llava_stablelm_1_6b",
"norm_eps": 1e-05,
"num_attention_heads": 32,
"num_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 32,
"rope_pct": 0.25,
"rope_theta": 10000,
"rotary_scaling_factor": 1.0,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 4096,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.37.0.dev0",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"use_qkv_bias": true,
"vocab_size": 100352
}