Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: NousResearch/Llama-2-7b-chat-hf
+base_model: NousResearch/Llama-2-13b-chat-hf
 tags:
 - trl
 - sft
@@ -13,10 +13,10 @@ library_name: peft
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/xiangchiyuan/huggingface/runs/l53izf26)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/xiangchiyuan/huggingface/runs/oue4pda2)
 # grammars_13bf
 
-This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) on the None dataset.
+This model is a fine-tuned version of [NousResearch/Llama-2-13b-chat-hf](https://huggingface.co/NousResearch/Llama-2-13b-chat-hf) on the None dataset.
 
 ## Model description
 
@@ -32,6 +32,21 @@ More information needed
 
 ## Training procedure
 
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- _load_in_8bit: True
+- _load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: False
+- load_in_8bit: True
 ### Training hyperparameters
 
 The following hyperparameters were used during training: