llmware/dragon-mistral-7b-v0-Ryobi_24_May

README.md

@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.11.1
-- Transformers 4.41.0
+- Transformers 4.40.2
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c6b06b0a8757e52f1d4437c1a9e53e579f671b33187f9f9059a6cf788809fa3
+oid sha256:f48694b58e302d178fb874185ff695f8f7d810acda36d89862ca006b38bd37d6
 size 109069176

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -31,6 +31,7 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5a8d63569281da245d535a9377f3a41575a271a3e15a585e9543ee4b745f13
-size 5112
+oid sha256:59d15b50bf068e3eb3f5e65268097a8ad8f265a28cd6b62083d73f921e524f2a
+size 4984