One complete epoch training
Browse files- adapter_config.json +7 -4
- adapter_model.safetensors +1 -1
adapter_config.json
CHANGED
@@ -6,6 +6,8 @@
|
|
6 |
},
|
7 |
"base_model_name_or_path": "sarvamai/sarvam-1",
|
8 |
"bias": "none",
|
|
|
|
|
9 |
"fan_in_fan_out": false,
|
10 |
"inference_mode": true,
|
11 |
"init_lora_weights": true,
|
@@ -14,6 +16,7 @@
|
|
14 |
"layers_to_transform": null,
|
15 |
"loftq_config": {},
|
16 |
"lora_alpha": 128,
|
|
|
17 |
"lora_dropout": 0.0,
|
18 |
"megatron_config": null,
|
19 |
"megatron_core": "megatron.core",
|
@@ -23,13 +26,13 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"up_proj",
|
27 |
-
"k_proj",
|
28 |
-
"gate_proj",
|
29 |
"q_proj",
|
|
|
30 |
"down_proj",
|
|
|
|
|
31 |
"lm_head",
|
32 |
-
"
|
33 |
],
|
34 |
"task_type": null,
|
35 |
"use_dora": false,
|
|
|
6 |
},
|
7 |
"base_model_name_or_path": "sarvamai/sarvam-1",
|
8 |
"bias": "none",
|
9 |
+
"eva_config": null,
|
10 |
+
"exclude_modules": null,
|
11 |
"fan_in_fan_out": false,
|
12 |
"inference_mode": true,
|
13 |
"init_lora_weights": true,
|
|
|
16 |
"layers_to_transform": null,
|
17 |
"loftq_config": {},
|
18 |
"lora_alpha": 128,
|
19 |
+
"lora_bias": false,
|
20 |
"lora_dropout": 0.0,
|
21 |
"megatron_config": null,
|
22 |
"megatron_core": "megatron.core",
|
|
|
26 |
"rank_pattern": {},
|
27 |
"revision": null,
|
28 |
"target_modules": [
|
|
|
|
|
|
|
29 |
"q_proj",
|
30 |
+
"up_proj",
|
31 |
"down_proj",
|
32 |
+
"gate_proj",
|
33 |
+
"v_projo_proj",
|
34 |
"lm_head",
|
35 |
+
"k_proj"
|
36 |
],
|
37 |
"task_type": null,
|
38 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 907982296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78c9c37dd4d3bee89a4d1379a7a34e16b8e3d4ff0936f3cbf8620ac7c82c4819
|
3 |
size 907982296
|