Training in progress, epoch 0
Browse files- adapter_config.json +14 -6
- adapter_model.safetensors +2 -2
adapter_config.json
CHANGED
|
@@ -1,11 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": {
|
| 4 |
-
"base_model_class": "
|
| 5 |
-
"parent_library": "
|
| 6 |
},
|
| 7 |
-
"base_model_name_or_path":
|
| 8 |
"bias": "none",
|
|
|
|
|
|
|
|
|
|
| 9 |
"fan_in_fan_out": false,
|
| 10 |
"inference_mode": true,
|
| 11 |
"init_lora_weights": "gaussian",
|
|
@@ -14,24 +17,29 @@
|
|
| 14 |
"layers_to_transform": null,
|
| 15 |
"loftq_config": {},
|
| 16 |
"lora_alpha": 8,
|
|
|
|
| 17 |
"lora_dropout": 0.1,
|
| 18 |
"megatron_config": null,
|
| 19 |
"megatron_core": "megatron.core",
|
| 20 |
"modules_to_save": null,
|
| 21 |
"peft_type": "LORA",
|
|
|
|
| 22 |
"r": 8,
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
-
"
|
| 27 |
"down_proj",
|
| 28 |
"up_proj",
|
| 29 |
-
"
|
| 30 |
-
"k_proj",
|
| 31 |
"v_proj",
|
|
|
|
| 32 |
"o_proj"
|
| 33 |
],
|
|
|
|
| 34 |
"task_type": null,
|
|
|
|
| 35 |
"use_dora": false,
|
|
|
|
| 36 |
"use_rslora": false
|
| 37 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
"auto_mapping": {
|
| 4 |
+
"base_model_class": "PeftModel",
|
| 5 |
+
"parent_library": "peft.peft_model"
|
| 6 |
},
|
| 7 |
+
"base_model_name_or_path": null,
|
| 8 |
"bias": "none",
|
| 9 |
+
"corda_config": null,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
"fan_in_fan_out": false,
|
| 13 |
"inference_mode": true,
|
| 14 |
"init_lora_weights": "gaussian",
|
|
|
|
| 17 |
"layers_to_transform": null,
|
| 18 |
"loftq_config": {},
|
| 19 |
"lora_alpha": 8,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
"lora_dropout": 0.1,
|
| 22 |
"megatron_config": null,
|
| 23 |
"megatron_core": "megatron.core",
|
| 24 |
"modules_to_save": null,
|
| 25 |
"peft_type": "LORA",
|
| 26 |
+
"qalora_group_size": 16,
|
| 27 |
"r": 8,
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": [
|
| 31 |
+
"gate_proj",
|
| 32 |
"down_proj",
|
| 33 |
"up_proj",
|
| 34 |
+
"q_proj",
|
|
|
|
| 35 |
"v_proj",
|
| 36 |
+
"k_proj",
|
| 37 |
"o_proj"
|
| 38 |
],
|
| 39 |
+
"target_parameters": null,
|
| 40 |
"task_type": null,
|
| 41 |
+
"trainable_token_indices": null,
|
| 42 |
"use_dora": false,
|
| 43 |
+
"use_qalora": false,
|
| 44 |
"use_rslora": false
|
| 45 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6ce51636de48d65e53a6bb2d9aa07e5a178e32615bd3e6d2f6b4491ae075bfa
|
| 3 |
+
size 89517224
|