mtasic85 commited on
Commit
9133dd4
·
1 Parent(s): eb7fc65
Files changed (1) hide show
  1. config.json +25 -7
config.json CHANGED
@@ -3,20 +3,38 @@
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
- "bos_token_id": 1,
7
- "eos_token_id": 2,
 
 
 
 
 
 
 
 
8
  "hidden_size": 512,
9
- "intermediate_size": 2048,
 
10
  "max_position_embeddings": 131072,
 
11
  "model_type": "llama",
12
- "num_hidden_layers": 32,
13
  "num_attention_heads": 16,
 
14
  "num_key_value_heads": 4,
 
15
  "rms_norm_eps": 1e-05,
16
- "rope_scaling": null,
17
- "tie_word_embeddings": false,
 
 
 
 
 
 
 
18
  "torch_dtype": "bfloat16",
19
- "transformers_version": "4.44.2",
20
  "use_cache": true,
21
  "vocab_size": 32768
22
  }
 
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": [
10
+ 1,
11
+ 4,
12
+ 5
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
  "hidden_size": 512,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
  "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
  "model_type": "llama",
 
22
  "num_attention_heads": 16,
23
+ "num_hidden_layers": 32,
24
  "num_key_value_heads": 4,
25
+ "pretraining_tp": 1,
26
  "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 32.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": true,
36
  "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.45.0.dev0",
38
  "use_cache": true,
39
  "vocab_size": 32768
40
  }