Laomaodiaoyu commited on
Commit
2d72cb1
·
verified ·
1 Parent(s): 323fb50

Upload 8 files

Browse files
LLaMA-Checkpoint/M3_N4_rank16/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "/home/share/zuojianhui/models/yahma/llama-7b-hf",
3
+ "bias": "none",
4
+ "enable_lora": null,
5
+ "expert_down": 3,
6
+ "expert_up": 4,
7
+ "fan_in_fan_out": false,
8
+ "inference_mode": true,
9
+ "lora_alpha": 32,
10
+ "lora_dropout": 0.05,
11
+ "merge_weights": false,
12
+ "modules_to_save": null,
13
+ "peft_type": "DROUTER",
14
+ "r": 16,
15
+ "target_modules": [
16
+ "q_proj",
17
+ "k_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
LLaMA-Checkpoint/M3_N4_rank16/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21d00b153d35ac9712ccc005e4df806b72d8ca4805691ee63f8337c175ff7bc
3
+ size 181219402
LLaMA-Checkpoint/M3_N8_rank8/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "/mnt/nodestor/wenhaokun/zuojianhui/models/llama-7b-hf",
3
+ "bias": "none",
4
+ "enable_lora": null,
5
+ "expert_down": 3,
6
+ "expert_up": 8,
7
+ "fan_in_fan_out": false,
8
+ "inference_mode": true,
9
+ "lora_alpha": 16,
10
+ "lora_dropout": 0.05,
11
+ "merge_weights": false,
12
+ "modules_to_save": null,
13
+ "peft_type": "DROUTER",
14
+ "r": 8,
15
+ "target_modules": [
16
+ "q_proj",
17
+ "k_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
LLaMA-Checkpoint/M3_N8_rank8/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83952782ba9b95f4af77d25c374a866ae543f6b31f3a5a86a42178f47a544c84
3
+ size 143609090
LLaMA2-Checkpoint/M3_N8_rank8/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "/home/share/zuojianhui/models/meta-llama/Llama-2-7B-hf",
3
+ "bias": "none",
4
+ "enable_lora": null,
5
+ "expert_down": 3,
6
+ "expert_up": 8,
7
+ "fan_in_fan_out": false,
8
+ "inference_mode": true,
9
+ "lora_alpha": 16,
10
+ "lora_dropout": 0.05,
11
+ "merge_weights": false,
12
+ "modules_to_save": null,
13
+ "peft_type": "DROUTER",
14
+ "r": 8,
15
+ "target_modules": [
16
+ "q_proj",
17
+ "k_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
LLaMA2-Checkpoint/M3_N8_rank8/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a174fcc2dda819247f6662381cfaa5ea2eeb810746b69f2d4e15b05de90a35ee
3
+ size 143609090
LLaMA2-Checkpoint/M4_N3_rank16/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "/home/share/zuojianhui/models/meta-llama/Llama-2-7B-hf",
3
+ "bias": "none",
4
+ "enable_lora": null,
5
+ "expert_down": 4,
6
+ "expert_up": 3,
7
+ "fan_in_fan_out": false,
8
+ "inference_mode": true,
9
+ "lora_alpha": 32,
10
+ "lora_dropout": 0.05,
11
+ "merge_weights": false,
12
+ "modules_to_save": null,
13
+ "peft_type": "DROUTER",
14
+ "r": 16,
15
+ "target_modules": [
16
+ "q_proj",
17
+ "k_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
LLaMA2-Checkpoint/M4_N3_rank16/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69c5b580c73f64cd9cef99d436e9bfd2bc3ccd8e6d84a9e5a7b1344012cce0c
3
+ size 182786186