elephi3

README.md

@@ -7,14 +7,14 @@ tags:
 - generated_from_trainer
 base_model: microsoft/Phi-3-mini-4k-instruct
 model-index:
-- name: phi3
+- name: elephi3
   results: []
 ---
 
 <!-- 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. -->
 
-# phi3
+# elephi3
 
 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.
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.42.3
+- Transformers 4.42.4
 - Pytorch 2.1.2
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "qkv_proj",
     "down_proj",
     "gate_up_proj",
-    "embed_tokens",
-    "qkv_proj"
+    "o_proj",
+    "embed_tokens"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005ddc8a510ec0191faa1cd3876b22d6f921c0ecd1a7086cdae20fbd4779050c
+oid sha256:728420ba06e737e9a69c8b7511479aaa75ac3b6365d487f99d61b6e8d5ea5fa9
 size 496949808

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 2048,
+    "max_length": 200,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1080a01b32f3081a6496eb343a90ca037ebaeedb38fa916277a702a4fdf21d9e
+oid sha256:4d25b21726b13a6ee7654f7d33cbe9fd05fc7899c90b5176ec974878adeab89e
 size 5368