mrzlab630 commited on
Commit
a2605ca
·
1 Parent(s): dc9e513

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +21 -15
config.json CHANGED
@@ -1,18 +1,24 @@
1
  {
2
- "base_model_name_or_path": "mrzlab630/weights_Llama_7b",
3
- "bias": "none",
4
- "enable_lora": null,
5
- "fan_in_fan_out": false,
6
- "inference_mode": true,
7
- "lora_alpha": 16,
8
- "lora_dropout": 0.05,
9
- "merge_weights": false,
10
- "modules_to_save": null,
11
- "peft_type": "LORA",
12
- "r": 8,
13
- "target_modules": [
14
- "q_proj",
15
- "v_proj"
16
  ],
17
- "task_type": "CAUSAL_LM"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
 
1
  {
2
+ "_name_or_path": "mrzlab630/weights_Llama_7b",
3
+ "architectures": [
4
+ "mrzlab630ForQuestionAnswering"
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 1,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 2048,
13
+ "max_sequence_length": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "pad_token_id": -1,
18
+ "rms_norm_eps": 1e-06,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float16",
21
+ "transformers_version": "4.31.0.dev0",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
  }