starcoder2-3b

README.md

@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.41.2
+- Transformers 4.42.3
 - Pytorch 2.3.0+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -21,10 +21,10 @@
   "revision": null,
   "target_modules": [
     "v_proj",
+    "q_proj",
+    "k_proj",
     "dense",
     "fc1",
-    "k_proj",
-    "q_proj",
     "fc2"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4365039c95cd702fbdb01ba08f98d628ba2267c550ad8898f1bc9e2623890cc3
+oid sha256:49669efbcdd224cd6cb7c0e5a814dfdaa26821686c7d520256824814d4161dc2
 size 24600064

tokenizer_config.json

@@ -349,9 +349,13 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 2048,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d52b0df78a059803ade58bf0476d0d2902269af9f720ed34806ed51f2585372
+oid sha256:63b8b30652ec5633e130ee254effec8f8c907df0ae72999faff46cf50a6d4250
 size 5368