oz1115/phi-3-mini-QLoRA-adapter

README.md

@@ -14,7 +14,6 @@ model-index:
 <!-- 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/gsitm/phi-3-mini-QLoRA/runs/a5amu4ck)
 # phi-3-mini-QLoRA
 
 This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
@@ -53,8 +52,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.11.1
-- Transformers 4.42.4
+- PEFT 0.12.0
+- Transformers 4.44.0
 - Pytorch 2.3.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
     "k_proj",
     "o_proj",
-    "v_proj",
-    "down_proj",
-    "up_proj",
-    "gate_proj",
-    "q_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6adcb61565d84963985e2370a78e4d0f4439152c6e4bc1bb9b37d2823949ebd6
+oid sha256:31e8c33602d963b527aef02955084cd84f66c498c5179d364b9c8861dead66e0
 size 35668592

special_tokens_map.json

@@ -13,13 +13,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "pad_token": "<unk>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer_config.json

@@ -121,15 +121,11 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "legacy": false,
-  "max_length": 512,
   "model_max_length": 4096,
   "pad_token": "<unk>",
   "padding_side": "left",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a0eb564f9aa3880098ef1e9105a6f0b5a1efedce3886fca8da19de8b4887fa
-size 5368
+oid sha256:c1f3f1fba257ee86d8eb0b4b9caa8d2e295d0c38487b19895aa741c773d40529
+size 5432