Upload folder using huggingface_hub

README.md

@@ -5,12 +5,12 @@ license: mit
 Chain of Thought (CoT) transformer model trained to do multi-step integer arithmetic.
 
 Model details:
- - **Vocabulary Size**: 40 (Character Tokenization)
+ - **Vocabulary Size**: 35 (Character Tokenization)
  - **Layer Count**: 8
  - **Attention Head Count**: 4
  - **Residual Stream Size**: 256
  - **Context Length**: 256
- - **Tokens Trained on**: 419,716,608
+ - **Tokens Trained on**: 419,706,880
 
 
 ```py
@@ -19,8 +19,7 @@ from transformers import pipeline
 pipe = pipeline(
     "text-generation", model="bart1259/MiniCOTMath"
 )
-print(pipe("Input: (5 + 5)
-", max_new_tokens=100)[0]["generated_text"])
+print(pipe("Input: (5 + 5)\n", max_new_tokens=100)[0]["generated_text"])
 ```
 
 Outputs:
@@ -60,8 +59,7 @@ class StopCriteria(StoppingCriteria):
     def __iter__(self):
         yield self
 
-prompt = "Input: (5 + 5)
-"
+prompt = "Input: (5 + 5)\n"
 
 tokenizer = AutoTokenizer.from_pretrained("bart1259/MiniCOTMath")
 model = AutoModelForCausalLM.from_pretrained("bart1259/MiniCOTMath").cuda()

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa529a29bee7d337ad783dc4ba51fbc70891014f441c7fd6921b535fd63295e
+oid sha256:b0e7b2d91eb4e7ea8bdc4b94640382a0af079b8e8e9974b801c9c48fdf4af330
 size 25352072