File size: 978 Bytes
8b71c34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "_name_or_path": "llmware/bling-qwen-1.5b",
  "aib_version": "model_archive_072424_qwen15_9440_0",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 1536,
  "initializer_range": 0.02,
  "intermediate_size": 8960,
  "max_position_embeddings": 131072,
  "max_window_layers": 28,
  "model_type": "qwen2",
  "num_attention_heads": 12,
  "num_hidden_layers": 28,
  "num_key_value_heads": 2,
  "rms_norm_eps": 1e-06,
  "rope_theta": 1000000.0,
  "sliding_window": 131072,
  "tie_word_embeddings": true,
  "trained": "custom training",
  "training_comments": "qwen2-15-core-read-gpt-9440-072424-0",
  "training_dataset": [
    "aib_label_samples_739.jsonl"
  ],
  "training_timestamp": "Wed Jul 24 09:03:22 2024",
  "transformers_version": "4.41.2",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}