Upload trained_t2l/gemma_2b_t2l/adapter_config.json with huggingface_hub
Browse files
trained_t2l/gemma_2b_t2l/adapter_config.json
CHANGED
@@ -3,6 +3,9 @@
|
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "google/gemma-2-2b-it",
|
5 |
"bias": "none",
|
|
|
|
|
|
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": false,
|
8 |
"init_lora_weights": true,
|
@@ -11,6 +14,7 @@
|
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
"lora_alpha": 16,
|
|
|
14 |
"lora_dropout": 0.05,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
@@ -20,10 +24,11 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
|
|
27 |
"use_dora": false,
|
28 |
-
"use_rslora":
|
29 |
}
|
|
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "google/gemma-2-2b-it",
|
5 |
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
"fan_in_fan_out": false,
|
10 |
"inference_mode": false,
|
11 |
"init_lora_weights": true,
|
|
|
14 |
"layers_to_transform": null,
|
15 |
"loftq_config": {},
|
16 |
"lora_alpha": 16,
|
17 |
+
"lora_bias": false,
|
18 |
"lora_dropout": 0.05,
|
19 |
"megatron_config": null,
|
20 |
"megatron_core": "megatron.core",
|
|
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
27 |
+
"q_proj",
|
28 |
+
"v_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
+
"trainable_token_indices": null,
|
32 |
"use_dora": false,
|
33 |
+
"use_rslora": true
|
34 |
}
|