kobu2 commited on
Commit
b95880a
1 Parent(s): 024fa18

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +32 -27
config.json CHANGED
@@ -1,29 +1,34 @@
1
  {
2
- "model_type": "llama",
3
- "architectures": ["LlamaForCausalLM"],
4
- "hidden_size": 8192,
5
- "intermediate_size": 32768,
6
- "num_attention_heads": 64,
7
- "num_hidden_layers": 80,
8
- "initializer_range": 0.02,
9
- "layer_norm_eps": 1e-5,
10
- "hidden_act": "silu",
11
- "vocab_size": 32000,
12
- "max_position_embeddings": 2048,
13
- "bos_token_id": 1,
14
- "eos_token_id": 2,
15
- "pad_token_id": 0,
16
- "tie_word_embeddings": false,
17
- "transformers_version": "4.28.0",
18
- "peft_config": {
19
- "r": 16,
20
- "lora_alpha": 16,
21
- "lora_dropout": 0,
22
- "bias": "none",
23
- "target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
24
- "use_gradient_checkpointing": true,
25
- "max_seq_length": 512,
26
- "use_rslora": false,
27
- "loftq_config": false
28
- }
 
 
 
 
 
29
  }
 
1
  {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/llama-3-8b-instruct-bnb-4bit",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": false,
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": "unsloth",
22
+ "target_modules": [
23
+ "down_proj",
24
+ "up_proj",
25
+ "o_proj",
26
+ "q_proj",
27
+ "v_proj",
28
+ "k_proj",
29
+ "gate_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
  }