Fix new line issue & Match vocab type to base model

README.md

@@ -29,10 +29,10 @@ These are the merged version: after training the adapters, we merge the original
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# model_name = "mistralai/Mistral-7B-v0.1 # Base Model
+# model_name = "mistralai/Mistral-7B-v0.1" # Base Model
 model_name = "h-j-han/Mistral-7B-VocADT-50k-Cyrillic" # Vocabulary Adapted Model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
 
 prefix = "\nEnglish: Hello!\nUkrainian: Добрий день!\nEnglish: How are you?\nUkrainian: Як справи?\nEnglish: "
 line = "Do you speak English?"
@@ -40,6 +40,8 @@ suffix = f"\nUkrainian:"
 prompt = prefix + line + suffix
 
 inputs = tokenizer(prompt, return_tensors="pt")
+for item in inputs:
+    inputs[item] = inputs[item].cuda()
 outputs = model.generate(**inputs, max_new_tokens=7)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 

config.json

@@ -21,5 +21,5 @@
     "torch_dtype": "bfloat16",
     "transformers_version": "4.43.0.dev0",
     "use_cache": true,
-    "vocab_size": 50303
+    "vocab_size": 50000
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aff296734aac9e047d1525a81dd197610f4c5668ce2ad377dd0950cea4e7980
-size 4975659888
+oid sha256:d195ff8bd0524853c5852b7c3fc99c45e50300df713899fd8a6d6c30fdf7523e
+size 4973177712

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db6882105dd368aac792a8ee20f9e6b2fcdd94113e5431b4a457902520075f0
-size 4891798312
+oid sha256:06b8123e8fd7f2131212a6246f8cd2dec41d75a25d14a0aaec704fbf6aaeb738
+size 4889316136

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 14783340544
+    "total_size": 14778376192
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",