shawmoon commited on
Commit
25bfb73
1 Parent(s): 1a699ea

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +27 -13
config.json CHANGED
@@ -1,16 +1,30 @@
1
  {
2
- "base_model_name_or_path": "bigscience/bloom-3b",
3
- "bias": "none",
4
- "fan_in_fan_out": false,
5
- "inference_mode": true,
6
- "init_lora_weights": true,
7
- "lora_alpha": 16,
8
- "lora_dropout": 0.05,
9
- "modules_to_save": null,
10
- "peft_type": "LORA",
11
- "r": 8,
12
- "target_modules": [
13
- "query_key_value"
14
  ],
15
- "task_type": "CAUSAL_LM"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  }
 
1
  {
2
+ "apply_residual_connection_post_layernorm": false,
3
+ "attention_dropout": 0.0,
4
+ "attention_softmax_in_fp32": true,
5
+ "bias_dropout_fusion": true,
6
+ "architectures": [
7
+ "BloomForCausalLM"
 
 
 
 
 
 
8
  ],
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "pad_token_id": 3,
12
+ "unk_token_id": 0,
13
+ "hidden_dropout": 0.0,
14
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "masked_softmax_fusion": true,
17
+ "model_type": "bloom",
18
+ "n_embed": 2560,
19
+ "n_inner": null,
20
+ "n_layer": 30,
21
+ "num_attention_heads": 32,
22
+ "offset_alibi": 100,
23
+ "pretraining_tp": 4,
24
+ "seq_length": 2048,
25
+ "skip_bias_add": true,
26
+ "skip_bias_add_qkv": false,
27
+ "transformers_version": "4.20.0",
28
+ "use_cache": true,
29
+ "vocab_size": 250880
30
  }