Files

76 lines
1.6 KiB
JSON
Raw Permalink Normal View History

{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "float32",
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 576,
"initializer_range": 0.041666666666666664,
"intermediate_size": 1536,
"is_llama_config": true,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 8192,
"max_window_layers": 28,
"mlp_bias": false,
"model_type": "qwen2",
"num_attention_heads": 9,
"num_hidden_layers": 30,
"num_key_value_heads": 3,
"pad_token_id": 2,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_interleaved": false,
"rope_parameters": {
"rope_theta": 100000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers.js_config": {
"kv_cache_dtype": {
"fp16": "float16",
"q4f16": "float16"
}
},
"transformers_version": "5.13.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 49152
}