File size: 1,614 Bytes
564ee42
37b8123
564ee42
 
 
 
 
37b8123
564ee42
 
 
 
37b8123
 
 
 
 
 
564ee42
 
 
 
 
 
 
 
 
 
 
 
 
 
37b8123
564ee42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "_name_or_path": "proteinglm-1b-mlm",
  "add_bias_linear": true,
  "add_qkv_bias": true,
  "apply_query_key_layer_scaling": true,
  "apply_residual_connection_post_layernorm": true,
  "architectures": [
    "ProteinGLMModel"
  ],
  "attention_dropout": 0.0,
  "attention_softmax_in_fp32": true,
  "auto_map": {
    "AutoConfig": "configuration_proteinglm.ProteinGLMConfig",
    "AutoModel": "modeling_proteinglm.ProteinGLMForMaskedLM",
    "AutoModelForCausalLM": "modeling_proteinglm.ProteinGLMForCasualLM",
    "AutoModelForMaskedLM": "modeling_proteinglm.ProteinGLMForMaskedLM",
    "AutoModelForSequenceClassification": "modeling_proteinglm.ProteinGLMForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_proteinglm.ProteinGLMForTokenClassification"
  },
  "bias_dropout_fusion": true,
  "deepnorm": true,
  "experts_per_token": 0,
  "ffn_hidden_size": 5461,
  "fp32_residual_connection": false,
  "glu_activation": "geglu",
  "head_num": 1,
  "hidden_dropout": 0.0,
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "is_causal": false,
  "kv_channels": 64,
  "layernorm_epsilon": 1e-05,
  "model_type": "ProteinGLM",
  "moe": false,
  "multi_query_attention": false,
  "multi_query_group_num": 1,
  "num_attention_heads": 32,
  "num_experts": 0,
  "num_layers": 24,
  "padded_vocab_size": 128,
  "post_layer_norm": true,
  "quantization_bit": 0,
  "rmsnorm": false,
  "rotary_embedding_2d": false,
  "seq_length": 1024,
  "torch_dtype": "float32",
  "transformers_version": "4.41.2",
  "untie_head": false,
  "use_cache": true,
  "use_pytorch_sdpa": true,
  "vocab_size": 128
}