qwen2-7b-longvila-1M / llm /config_slidingwindow.json
Yukang's picture
Add model files
c10ef1b
raw
history blame contribute delete
915 Bytes
{
"_name_or_path": "./output/qwen2-vl-7b-dynamic-sft-512k-2048frames-7nodes/llm",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 524288,
"max_window_layers": -1,
"model_max_length": 524288,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"factor": 4.0,
"type": "linear"
},
"rope_theta": 1062356830,
"sliding_window": 128,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 524288,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.44.2",
"use_cache": true,
"use_sliding_window": true,
"vocab_size": 151648
}