Prathamesh25 commited on
Commit
f911eb6
·
verified ·
1 Parent(s): f70c3db

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +18 -16
config.json CHANGED
@@ -1,24 +1,26 @@
1
  {
 
2
  "architectures": [
3
- "AutoModelForCausalLM"
4
  ],
5
- "attention_probs_dropout_prob": 0.1,
6
- "hidden_dropout_prob": 0.1,
7
- "hidden_size": 2048,
8
- "intermediate_size": 8192,
9
- "layer_norm_eps": 1e-05,
 
10
  "max_position_embeddings": 4096,
11
  "model_type": "llama",
12
- "num_attention_heads": 128,
13
  "num_hidden_layers": 32,
14
- "output_past": true,
15
- "pad_token_id": 50256,
16
- "vocab_size": 50257,
17
- "use_cache": false,
18
  "pretraining_tp": 1,
19
- "lora_alpha": 16,
20
- "lora_dropout": 0.1,
21
- "r": 64,
22
- "bias": "none",
23
- "task_type": "CAUSAL_LM"
 
 
24
  }
 
1
  {
2
+ "_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
  "max_position_embeddings": 4096,
13
  "model_type": "llama",
14
+ "num_attention_heads": 32,
15
  "num_hidden_layers": 32,
16
+ "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
 
 
18
  "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
  }