File size: 1,026 Bytes
204ab68 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 |
{
"_name_or_path": "Qwen/Qwen2-72B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 29568,
"max_position_embeddings": 32768,
"max_window_layers": 80,
"model_type": "qwen2",
"num_attention_heads": 64,
"num_hidden_layers": 86,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.41.0",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151646,
"quantization_config": {
"quant_method": "exl2",
"version": "0.1.8",
"bits": 6.0,
"head_bits": 6,
"calibration": {
"rows": 115,
"length": 2048,
"dataset": "(default)"
}
}
} |