llama-2-7b-mlabonne-enhanced

README.md

@@ -5,6 +5,7 @@ tags:
 model-index:
 - name: results_modified
   results: []
+library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -28,6 +29,17 @@ More information needed
 
 ## Training procedure
 
+
+The following `bitsandbytes` quantization config was used during training:
+- load_in_8bit: False
+- load_in_4bit: True
+- 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: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
@@ -46,6 +58,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.4.0
 - Transformers 4.31.0
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.2

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de64f3f1356542de77d67de589b41dc308d82055be5bbabde0fbd91e73b0f20c
+oid sha256:ad2931fd6a35c321f7cad63c84d3be9e76851a3d8e88bc16ca42718706acce29
 size 16823434

runs/Jun10_10-28-29_6df5ae60d2e1/events.out.tfevents.1718015594.6df5ae60d2e1.1067.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7dfd9879baa072b27a7036f8a579ee0c4fb10a3fdc876825f8da2ab387f37f7
+size 4741

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60c5583b764b48245c606f011cfa670e82fcd58f5fad08cdb4f50517e7747b32
+oid sha256:0394b5dba13ac749882d428f7d20bbe55c3c03f569e91b692db43a867c4edb74
 size 4408