BlackSamorez
commited on
Commit
•
ad9c9da
1
Parent(s):
36753db
Upload model
Browse files- adapter_config.json +39 -6
- adapter_model.bin +2 -2
adapter_config.json
CHANGED
@@ -1,18 +1,51 @@
|
|
1 |
{
|
2 |
-
"base_model_name_or_path": "
|
3 |
"bias": "none",
|
4 |
"enable_lora": null,
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
7 |
-
"lora_alpha":
|
8 |
"lora_dropout": 0.05,
|
9 |
"merge_weights": false,
|
10 |
"modules_to_save": null,
|
11 |
"peft_type": "LORA",
|
12 |
-
"r":
|
13 |
"target_modules": [
|
14 |
-
"q_proj",
|
15 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
],
|
17 |
-
"task_type":
|
18 |
}
|
|
|
1 |
{
|
2 |
+
"base_model_name_or_path": "IlyaGusev/llama_7b_ru_turbo_alpaca_lora_merged",
|
3 |
"bias": "none",
|
4 |
"enable_lora": null,
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
7 |
+
"lora_alpha": 32,
|
8 |
"lora_dropout": 0.05,
|
9 |
"merge_weights": false,
|
10 |
"modules_to_save": null,
|
11 |
"peft_type": "LORA",
|
12 |
+
"r": 32,
|
13 |
"target_modules": [
|
14 |
+
"model.layers.27.self_attn.q_proj",
|
15 |
+
"model.layers.27.self_attn.k_proj",
|
16 |
+
"model.layers.27.self_attn.v_proj",
|
17 |
+
"model.layers.27.self_attn.o_proj",
|
18 |
+
"model.layers.27.mlp.gate_proj",
|
19 |
+
"model.layers.27.mlp.down_proj",
|
20 |
+
"model.layers.27.mlp.up_proj",
|
21 |
+
"model.layers.28.self_attn.q_proj",
|
22 |
+
"model.layers.28.self_attn.k_proj",
|
23 |
+
"model.layers.28.self_attn.v_proj",
|
24 |
+
"model.layers.28.self_attn.o_proj",
|
25 |
+
"model.layers.28.mlp.gate_proj",
|
26 |
+
"model.layers.28.mlp.down_proj",
|
27 |
+
"model.layers.28.mlp.up_proj",
|
28 |
+
"model.layers.29.self_attn.q_proj",
|
29 |
+
"model.layers.29.self_attn.k_proj",
|
30 |
+
"model.layers.29.self_attn.v_proj",
|
31 |
+
"model.layers.29.self_attn.o_proj",
|
32 |
+
"model.layers.29.mlp.gate_proj",
|
33 |
+
"model.layers.29.mlp.down_proj",
|
34 |
+
"model.layers.29.mlp.up_proj",
|
35 |
+
"model.layers.30.self_attn.q_proj",
|
36 |
+
"model.layers.30.self_attn.k_proj",
|
37 |
+
"model.layers.30.self_attn.v_proj",
|
38 |
+
"model.layers.30.self_attn.o_proj",
|
39 |
+
"model.layers.30.mlp.gate_proj",
|
40 |
+
"model.layers.30.mlp.down_proj",
|
41 |
+
"model.layers.30.mlp.up_proj",
|
42 |
+
"model.layers.31.self_attn.q_proj",
|
43 |
+
"model.layers.31.self_attn.k_proj",
|
44 |
+
"model.layers.31.self_attn.v_proj",
|
45 |
+
"model.layers.31.self_attn.o_proj",
|
46 |
+
"model.layers.31.mlp.gate_proj",
|
47 |
+
"model.layers.31.mlp.down_proj",
|
48 |
+
"model.layers.31.mlp.up_proj"
|
49 |
],
|
50 |
+
"task_type": null
|
51 |
}
|
adapter_model.bin
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 sha256:11610b76aba2b0e071d9f39e0dac591743771ebd412de0b75860045d2027e797
|
3 |
+
size 49996163
|