altomek commited on
Commit
9b290a5
1 Parent(s): 045675d

Update config.json

Browse files

Adding pad_token_id.

Files changed (1) hide show
  1. config.json +40 -39
config.json CHANGED
@@ -1,40 +1,41 @@
1
- {
2
- "_name_or_path": "new-dawn-llama3-70b-32K-v1.0",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": 128001,
10
- "hidden_act": "silu",
11
- "hidden_size": 8192,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 28672,
14
- "max_position_embeddings": 32768,
15
- "model_type": "llama",
16
- "num_attention_heads": 64,
17
- "num_hidden_layers": 80,
18
- "num_key_value_heads": 8,
19
- "pretraining_tp": 1,
20
- "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
22
- "rope_theta": 3000000.0,
23
- "tie_word_embeddings": false,
24
- "torch_dtype": "float16",
25
- "transformers_version": "4.36.2",
26
- "use_cache": true,
27
- "use_flash_attention_2": true,
28
- "vocab_size": 128256,
29
- "quantization_config": {
30
- "quant_method": "exl2",
31
- "version": "0.1.0",
32
- "bits": 4.0,
33
- "head_bits": 8,
34
- "calibration": {
35
- "rows": 100,
36
- "length": 2048,
37
- "dataset": "(default)"
38
- }
39
- }
 
40
  }
 
1
+ {
2
+ "_name_or_path": "new-dawn-llama3-70b-32K-v1.0",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "pad_token_id": 128002,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 8192,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 28672,
15
+ "max_position_embeddings": 32768,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 80,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 3000000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.36.2",
27
+ "use_cache": true,
28
+ "use_flash_attention_2": true,
29
+ "vocab_size": 128256,
30
+ "quantization_config": {
31
+ "quant_method": "exl2",
32
+ "version": "0.1.0",
33
+ "bits": 4.0,
34
+ "head_bits": 8,
35
+ "calibration": {
36
+ "rows": 100,
37
+ "length": 2048,
38
+ "dataset": "(default)"
39
+ }
40
+ }
41
  }