dcbv
/

PEFT
rondlite commited on
Commit
1d12ccc
1 Parent(s): 2048534
adapter_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "models/TehVenom_Pygmalion-13b-Merged",
3
+ "bias": "none",
4
+ "fan_in_fan_out": false,
5
+ "inference_mode": true,
6
+ "init_lora_weights": true,
7
+ "lora_alpha": 1024,
8
+ "lora_dropout": 0.05,
9
+ "modules_to_save": null,
10
+ "peft_type": "LORA",
11
+ "r": 512,
12
+ "target_modules": [
13
+ "q_proj",
14
+ "v_proj"
15
+ ],
16
+ "task_type": "CAUSAL_LM"
17
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a431dfa6b56cfd104b75587d560d610b630e06115d8d322b5f78f02b75c18c7b
3
+ size 1677779533
training_parameters.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"lora_name": "charluv-lora", "always_override": true, "save_steps": 0.0, "micro_batch_size": 4, "batch_size": 128, "epochs": 12.0, "learning_rate": "3e-5", "lr_scheduler_type": "cosine_with_restarts", "lora_rank": 512, "lora_alpha": 1024, "lora_dropout": 0.05, "cutoff_len": 256, "dataset": "None", "eval_dataset": "None", "format": "None", "eval_steps": 100.0, "raw_text_file": "aiva", "overlap_len": 128, "newline_favor_len": 128, "do_shuffle": true, "higher_rank_limit": false, "warmup_steps": 100.0, "optimizer": "sgd"}