File size: 1,477 Bytes
66205fa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
{
  "alpha_pattern": {},
  "auto_mapping": null,
  "base_model_name_or_path": "google/gemma-3n-E2B-it",
  "bias": "none",
  "corda_config": null,
  "eva_config": null,
  "exclude_modules": null,
  "fan_in_fan_out": false,
  "inference_mode": true,
  "init_lora_weights": true,
  "layer_replication": null,
  "layers_pattern": null,
  "layers_to_transform": null,
  "loftq_config": {},
  "lora_alpha": 32,
  "lora_bias": false,
  "lora_dropout": 0.05,
  "megatron_config": null,
  "megatron_core": "megatron.core",
  "modules_to_save": null,
  "peft_type": "LORA",
  "qalora_group_size": 16,
  "r": 16,
  "rank_pattern": {},
  "revision": null,
  "target_modules": [
    "ffw_layer_2",
    "linear_end",
    "altup_projections.1",
    "post",
    "pos_proj",
    "gate_proj",
    "o_proj",
    "up_proj",
    "v_proj",
    "prediction_coefs",
    "modality_router",
    "correction_coefs",
    "linear_start",
    "per_layer_model_projection",
    "altup_unembed_projections.0",
    "linear_left",
    "input_proj_linear",
    "k_proj",
    "per_layer_input_gate",
    "per_layer_projection",
    "embedding_projection",
    "altup_unembed_projections.1",
    "altup_unembed_projections.2",
    "q_proj",
    "altup_projections.2",
    "ffw_layer_1",
    "linear_right",
    "down_proj",
    "altup_projections.0"
  ],
  "target_parameters": null,
  "task_type": "CAUSAL_LM",
  "trainable_token_indices": null,
  "use_dora": false,
  "use_qalora": false,
  "use_rslora": false
}