Update README.md

README.md

@@ -3,55 +3,18 @@ pipeline_tag: text-generation
 license: apache-2.0
 language:
 - en
-tags:
-- SOLAR-10.7B-v1.0
-- Open-platypus-Commercial
-base_model: upstage/SOLAR-10.7B-v1.0
+base_model: liminerity/M7-7b
 datasets:
-- kyujinpy/Open-platypus-Commercial
+- Intel/orca_dpo_pairs
 model-index:
-- name: T3Q-platypus-SOLAR-10.7B-v1.0
+- name: T3Q-DPO-Mistral-7B
   results: []
 ---
-Update @ 2024.03.07
+Update @ 2024.03.13
 
-## T3Q-platypus-SOLAR-10.7B-v1.0
+## T3Q-DPO-Mistral-7B
 
-This model is a fine-tuned version of upstage/SOLAR-10.7B-v1.0
+This model is a DPO fine-tuned version of liminerity/M7-7b
 
 **Model Developers** Chihoon Lee(chlee10), T3Q
 
-## Training hyperparameters
-
-The following hyperparameters were used during training:
-
-```python
-  # 데이터셋과 훈련 횟수와 관련된 하이퍼 파라미터
-  batch_size = 16
-  num_epochs = 1
-  micro_batch = 1
-  gradient_accumulation_steps = batch_size // micro_batch
-  
-  # 훈련 방법에 대한 하이퍼 파라미터
-  cutoff_len = 4096
-  lr_scheduler = 'cosine'
-  warmup_ratio = 0.06 # warmup_steps = 100
-  learning_rate = 4e-4
-  optimizer = 'adamw_torch'
-  weight_decay = 0.01
-  max_grad_norm = 1.0
-  
-  # LoRA config
-  lora_r = 16
-  lora_alpha = 16
-  lora_dropout = 0.05
-  lora_target_modules = ["gate_proj", "down_proj", "up_proj"]
-  
-  # Tokenizer에서 나오는 input값 설정 옵션
-  train_on_inputs = False
-  add_eos_token = False
-  
-  # NEFTune params
-  noise_alpha: int = 5
-```
-