Text Generation
Transformers
PyTorch
English
beit3_llava
Inference Endpoints
RLHF-V / config.json
finalf0's picture
Upload 7 files
3ea985a
raw
history blame
892 Bytes
{
"_name_or_path": "../Muffin_checkpoints/vqa_exp/muffin_13b_SFT-no_crop_0.99-vqav2-train#unimm-chat-50#50-beit3_large_patch16_448/checkpionts/checkpoint-2800/",
"architectures": [
"Beit3LlavaLlamaForCausalLM"
],
"bos_token_id": 0,
"eos_token_id": 1,
"freeze_mm_mlp_adapter": false,
"fully_tune": true,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_sequence_length": 2048,
"mm_use_im_start_end": true,
"mm_vision_tower": "beit3_large_patch16_448",
"model_type": "beit3_llava",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_query": 64,
"pad_token_id": -1,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.28.0.dev0",
"tune_mm_mlp_adapter": false,
"use_cache": false,
"use_mm_proj": true,
"vocab_size": 32004
}