anyiwang/mistral_4

adapter_config.json

@@ -10,7 +10,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:509784fb7423f7cc0036374d59fe7db82a4abba7812b6c0c1cf6b8fbe97ed25e
+oid sha256:2cd0624f8acbb42eff8a8476a5d062158819a539e34906a1b7ba09d61fe9f527
 size 694431312

special_tokens_map.json

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

tokenizer_config.json

@@ -34,11 +34,15 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
+  "max_length": 1024,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
+  "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:f4461e7089d884f5340bee8fed27c326dd9c052c681cc9aff782e825bbd37618
+oid sha256:5bd2b7c10a3b914e471e69e68a81b4a3ab6ec9160ada513d52cd7978f2de582f
 size 5496