Hugging Face's logo

Aleph-Alpha
/
llama-3_1-8b-tfree-hat-dpo

Safetensors
PyTorch
English
German
hierarchical_autoregressive_transformer
Aleph Alpha Research
Hirarchical Autoregressive Transformer
HAT
custom_code
Model card Files Community
llama-3_1-8b-tfree-hat-dpo
File size: 2,324 Bytes 
0d66674
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
 
{
  "auto_map": {
    "AutoConfig": "config.HATArchitectureConfig",
    "AutoModelForCausalLM": "model.HATForCausalLM"
  },
  "backbone_config": {
    "hidden_size": 4096,
    "intermediate_size": 14336,
    "max_position_embeddings": 32768,
    "mlp_bias": false,
    "num_attention_heads": 32,
    "num_hidden_layers": 32,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "factor": 8.0,
      "high_freq_factor": 4.0,
      "low_freq_factor": 1.0,
      "original_max_position_embeddings": 8192,
      "rope_type": "llama3"
    },
    "rope_theta": 500000,
    "sliding_window": null,
    "transformers_version": null,
    "use_cache": true,
    "vocab_size": 0
  },
  "decoder_config": {
    "cross_attention_config": {
      "attention_num_kv_heads": 8,
      "hidden_size": 1024,
      "hidden_size_kv": 4096,
      "hidden_size_q": 1024,
      "num_attention_heads": 8,
      "word_window_size": 1
    },
    "cross_attn_every_layer": true,
    "hidden_size": 1024,
    "intermediate_size": 2816,
    "max_position_embeddings": 262144,
    "mlp_bias": false,
    "num_attention_heads": 8,
    "num_hidden_layers": 4,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "rope_type": "default"
    },
    "rope_theta": 100000,
    "sliding_window": 768,
    "transformers_version": null,
    "use_cache": true,
    "vocab_size": 256
  },
  "encoder_config": {
    "cross_attention_config": {
      "attention_num_kv_heads": 32,
      "hidden_size": 4096,
      "hidden_size_kv": 1024,
      "hidden_size_q": 4096,
      "num_attention_heads": 32,
      "word_window_size": 1
    },
    "hidden_size": 1024,
    "intermediate_size": 2816,
    "max_position_embeddings": 262144,
    "mlp_bias": false,
    "num_attention_heads": 8,
    "num_hidden_layers": 6,
    "num_key_value_heads": 8,
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
      "rope_type": "default"
    },
    "rope_theta": 100000,
    "sliding_window": 768,
    "transformers_version": null,
    "use_cache": true,
    "vocab_size": 256
  },
  "model_type": "hierarchical_autoregressive_transformer",
  "special_token_dict": {
    "<|begin_of_text|>": 250,
    "<|end_header_id|>": 252,
    "<|eot_id|>": 192,
    "<|start_header_id|>": 251
  },
  "transformers_version": "4.46.3"
}