vilsonrodrigues commited on
Commit
b96e666
1 Parent(s): 55863b9

synchronizing config file

Browse files
Files changed (1) hide show
  1. config.json +13 -13
config.json CHANGED
@@ -1,18 +1,17 @@
1
  {
2
- "_name_or_path": "tiiuae/falcon-7b",
3
  "alibi": false,
4
  "apply_residual_connection_post_layernorm": false,
5
  "architectures": [
6
- "RWForCausalLM"
7
  ],
8
  "attention_dropout": 0.0,
9
  "auto_map": {
10
- "AutoConfig": "tiiuae/falcon-7b--configuration_RW.RWConfig",
11
- "AutoModel": "tiiuae/falcon-7b--modelling_RW.RWModel",
12
- "AutoModelForCausalLM": "tiiuae/falcon-7b--modelling_RW.RWForCausalLM",
13
- "AutoModelForQuestionAnswering": "tiiuae/falcon-7b--modelling_RW.RWForQuestionAnswering",
14
- "AutoModelForSequenceClassification": "tiiuae/falcon-7b--modelling_RW.RWForSequenceClassification",
15
- "AutoModelForTokenClassification": "tiiuae/falcon-7b--modelling_RW.RWForTokenClassification"
16
  },
17
  "bias": false,
18
  "bos_token_id": 11,
@@ -21,13 +20,14 @@
21
  "hidden_size": 4544,
22
  "initializer_range": 0.02,
23
  "layer_norm_epsilon": 1e-05,
24
- "model_type": "RefinedWebModel",
25
  "multi_query": true,
26
- "n_head": 71,
27
- "n_layer": 32,
 
28
  "parallel_attn": true,
29
- "torch_dtype": "float32",
30
- "transformers_version": "4.31.0.dev0",
31
  "use_cache": true,
32
  "vocab_size": 65024
33
  }
 
1
  {
 
2
  "alibi": false,
3
  "apply_residual_connection_post_layernorm": false,
4
  "architectures": [
5
+ "FalconForCausalLM"
6
  ],
7
  "attention_dropout": 0.0,
8
  "auto_map": {
9
+ "AutoConfig": "configuration_falcon.FalconConfig",
10
+ "AutoModel": "modeling_falcon.FalconModel",
11
+ "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
12
+ "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",
13
+ "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"
15
  },
16
  "bias": false,
17
  "bos_token_id": 11,
 
20
  "hidden_size": 4544,
21
  "initializer_range": 0.02,
22
  "layer_norm_epsilon": 1e-05,
23
+ "model_type": "falcon",
24
  "multi_query": true,
25
+ "new_decoder_architecture": false,
26
+ "num_attention_heads": 71,
27
+ "num_hidden_layers": 32,
28
  "parallel_attn": true,
29
+ "torch_dtype": "bfloat16",
30
+ "transformers_version": "4.27.4",
31
  "use_cache": true,
32
  "vocab_size": 65024
33
  }