Upload model

README.md

@@ -1,14 +1,6 @@
 ---
 library_name: peft
-license: mit
-datasets:
-- yahma/alpaca-cleaned
-pipeline_tag: text-generation
 ---
-
-## Quantized LLaMA2 Alpaca
-**quantized-llama2-alpaca** is a fine-tuned version of the [LLaMA2](https://ai.meta.com/research/publications/llama-2-open-foundation-and-fine-tuned-chat-models/) ([Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b)) model on the [Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset using [QLoRA](https://arxiv.org/abs/2305.14314).
-
 ## Training procedure
 
 
@@ -22,8 +14,7 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_quant_type: nf4
 - bnb_4bit_use_double_quant: True
 - bnb_4bit_compute_dtype: bfloat16
-  
 ### Framework versions
 
 
-- PEFT 0.4.0
+- PEFT 0.4.0

adapter_config.json

@@ -14,13 +14,13 @@
   "r": 64,
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "q_proj",
+    "k_proj",
     "gate_proj",
-    "down_proj",
-    "o_proj",
+    "v_proj",
     "up_proj",
-    "k_proj",
-    "q_proj"
+    "o_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }