Hugging Face's logo

Neko-Institute-of-Science
/
LLaMA-13B-8bit-LoRA-LightNovels

Model card Files Community
1
Neko-Institute-of-Science commited on
Commit
6434efc
•
1 Parent(s): a119e81

23/150 Hours

Browse files
Files changed (29) hide show
  1. checkpoint-1248/adapter_config.json +17 -0
  2. checkpoint-1248/adapter_model.bin +3 -0
  3. checkpoint-1664/adapter_config.json +17 -0
  4. checkpoint-1664/adapter_model.bin +3 -0
  5. checkpoint-2080/adapter_config.json +17 -0
  6. checkpoint-2080/adapter_model.bin +3 -0
  7. checkpoint-2496/adapter_config.json +17 -0
  8. checkpoint-2496/adapter_model.bin +3 -0
  9. checkpoint-2912/adapter_config.json +17 -0
  10. checkpoint-2912/adapter_model.bin +3 -0
  11. checkpoint-3328/adapter_config.json +17 -0
  12. checkpoint-3328/adapter_model.bin +3 -0
  13. checkpoint-3744/adapter_config.json +17 -0
  14. checkpoint-3744/adapter_model.bin +3 -0
  15. checkpoint-416/adapter_config.json +17 -0
  16. checkpoint-416/adapter_model.bin +3 -0
  17. checkpoint-4160/adapter_config.json +17 -0
  18. checkpoint-4160/adapter_model.bin +3 -0
  19. checkpoint-4576/adapter_config.json +17 -0
  20. checkpoint-4576/adapter_model.bin +3 -0
  21. checkpoint-4992/adapter_config.json +17 -0
  22. checkpoint-4992/adapter_model.bin +3 -0
  23. checkpoint-5408/adapter_config.json +17 -0
  24. checkpoint-5408/adapter_model.bin +3 -0
  25. checkpoint-5824/adapter_config.json +17 -0
  26. checkpoint-5824/adapter_model.bin +3 -0
  27. checkpoint-832/adapter_config.json +17 -0
  28. checkpoint-832/adapter_model.bin +3 -0
  29. training_parameters.json +1 -0
checkpoint-1248/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-1248/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674ef686e61b33bd71270d8fac4534c92eaa8111a5b28478fd1f49bf5ae9bfee
3
+ size 838918733
checkpoint-1664/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-1664/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd1c28fc8f75321a71ed3d79891a4e9e7515243bc4d92cd1a0e038ea7ba9bcad
3
+ size 838918733
checkpoint-2080/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-2080/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a959b1c89d27f91fa225aa4892e07e150915ac37c0ecf19b71c94f6e04d69f9
3
+ size 838918733
checkpoint-2496/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-2496/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a384984c1e2b93dd40d0b6f31b5511acefab75162a0c6e1ad1929c83528741c4
3
+ size 838918733
checkpoint-2912/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-2912/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ce8b4e6f9b4a4f6783987db47e34d8c859816e0ef3a6715fb6de5f54cc49117
3
+ size 838918733
checkpoint-3328/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-3328/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:155ef17fed8fc7d4568a5e80b56dc6350e4c5e9fae54bbd422410cf96e785125
3
+ size 838918733
checkpoint-3744/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-3744/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0caf6d56c4815d2ad5378f3bac281e5cbc24c6849ccabbcaf26fba039f76231
3
+ size 838918733
checkpoint-416/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-416/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e5db4ef7912abadf1976e3fa3e171c7bb32685b476f6712e046712ce4708bd5
3
+ size 838918733
checkpoint-4160/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-4160/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10b7dfecd54a9ed1dba450819eec4fcd1eb16847eb4473dc76b2642ba3b46675
3
+ size 838918733
checkpoint-4576/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-4576/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91e076344275bdbc4f30d5243b0cace1a8d2c0874ed75305d85b3060a12d98b1
3
+ size 838918733
checkpoint-4992/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-4992/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20ba7fa868fc62aa5fbe9ff2e897e7c551cda46384f9ab7cb94d6426f5c50542
3
+ size 838918733
checkpoint-5408/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-5408/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48078bea5ea8ea69cc052e22b74d291d4d0f874a18180046db13c57b982f42e2
3
+ size 838918733
checkpoint-5824/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-5824/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b8a670041222ff33399eeb22747a86f7ff8cb0e0959f1bed7d0d9061f064e4
3
+ size 838918733
checkpoint-832/adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/llama-13b",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 512,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 256,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
checkpoint-832/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af4068daca68b5f524a373f4fa68c94502fcc89afee6d9f38e5d94990515e8c
3
+ size 838918733
training_parameters.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"lora_name": "LightNovels", "always_override": false, "save_steps": 400.0, "micro_batch_size": 4, "batch_size": 128, "epochs": 1.0, "learning_rate": "3e-4", "lr_scheduler_type": "constant", "lora_rank": 256, "lora_alpha": 512, "lora_dropout": 0.05, "cutoff_len": 2048, "dataset": "None", "eval_dataset": "None", "format": "None", "eval_steps": 100.0, "raw_text_file": "LightNovels_clean", "overlap_len": 512, "newline_favor_len": 512, "do_shuffle": true, "higher_rank_limit": false, "warmup_steps": 100.0, "optimizer": "adamw_torch"}