Update README.md

README.md

@@ -19,6 +19,16 @@ This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggin
 It achieves the following results on the evaluation set:
 - Loss: 0.3878
 
+Test set:
+- BLEU: 65.06
+- COMET: 89.13
+- CodeBLEU: 78.52
+  - N-gram match score: 66.81
+  - Weighted n-gram match score: 82.49
+  - Syntax match score: 75.77
+  - Dataflow match score: 89.02
+
+
 ## Model description
 
 More information needed
@@ -63,24 +73,5 @@ The following hyperparameters were used during training:
 - Datasets 3.0.1
 - Tokenizers 0.13.3
 
-## Use this model
-
-```
-from transformers import AutoModelForCausalLM
-from transformers import BitsAndBytesConfig
-import torch
-
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_quant_type="nf4",
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_compute_dtype=torch.bfloat16,
-)
-
-model = AutoModelForCausalLM.from_pretrained(
-    "hugo-albert/CodeLlama-7b-hf-finetuned-py-to-cpp",
-    quantization_config=quantization_config,
-    torch_dtype=torch.bfloat16,
-)
 
 ```