add codellama models

data/code_eval_board.csv

@@ -1,17 +1,26 @@
 T,Models,Size (B),Win Rate,Throughput (tokens/s),Seq_length,#Languages,humaneval-python,java,javascript,cpp,php,julia,d,Average score,lua,r,racket,rust,swift,Throughput (tokens/s) bs=50,Peak Memory (MB),models_query,Links
-🔶,WizardCoder-15B-V1.0,15.0,15.31,43.7,8192,86,58.12,35.77,41.91,38.95,39.34,33.98,12.14,32.07,27.85,22.53,13.39,33.74,27.06,1470.0,32414,WizardCoder-15B-V1.0,https://huggingface.co/WizardLM/WizardCoder-15B-V1.0
-🔶,OctoCoder-15B,15.0,13.31,44.4,8192,86,45.3,26.03,32.8,29.32,26.76,24.5,13.35,24.01,22.56,14.39,10.61,24.26,18.24,1520.0,32278,OctoCoder-15B,https://huggingface.co/bigcode/octocoder
-🟢,StarCoder-15B,15.0,12.96,43.9,8192,86,33.57,30.22,30.79,31.55,26.08,23.02,13.57,22.74,23.89,15.5,0.07,21.84,22.74,1490.0,33461,StarCoder-15B,https://huggingface.co/bigcode/starcoder
-🟢,StarCoderBase-15B,15.0,12.69,43.8,8192,86,30.35,28.53,31.7,30.56,26.75,21.09,10.01,22.4,26.61,10.18,11.77,24.46,16.74,1460.0,32366,StarCoderBase-15B,https://huggingface.co/bigcode/starcoderbase
-🟢,CodeGeex2-6B,6.0,10.96,32.7,8192,100,33.49,23.46,29.9,28.45,25.27,20.93,8.44,21.23,15.94,14.58,11.75,20.45,22.06,982.0,14110,CodeGeex2-6B,https://huggingface.co/THUDM/codegeex2-6b
-🟢,StarCoderBase-7B,7.0,10.92,46.9,8192,86,28.37,24.44,27.35,23.3,22.12,21.77,8.1,20.17,23.35,14.51,11.08,22.6,15.1,1700.0,16512,StarCoderBase-7B,https://huggingface.co/bigcode/starcoderbase-7b
-🔶,OctoGeeX-7B,7.0,10.5,32.7,8192,100,42.28,19.33,28.5,23.93,25.85,22.94,9.77,20.79,16.19,13.66,12.02,17.94,17.03,982.0,14110,OctoGeeX-7B,https://huggingface.co/bigcode/octogeex
-🟢,CodeGen25-7B-multi,7.0,9.81,32.6,2048,86,28.7,26.01,26.27,25.75,21.98,19.11,8.84,20.04,23.44,11.59,10.37,21.84,16.62,680.0,15336,CodeGen25-7B-multi,https://huggingface.co/Salesforce/codegen25-7b-multi
-🟢,StarCoderBase-3B,3.0,7.77,50.0,8192,86,21.5,19.25,21.32,19.43,18.55,16.1,4.97,15.29,18.04,10.1,7.87,16.32,9.98,1770.0,8414,StarCoderBase-3B,https://huggingface.co/bigcode/starcoderbase-3b
-🟢,Replit-2.7B,2.7,5.85,42.2,2048,20,20.12,21.39,20.18,20.37,16.14,1.24,6.41,11.62,2.11,7.2,3.22,15.19,5.88,577.0,7176,Replit-2.7B,https://huggingface.co/replit/replit-code-v1-3b
-🟢,StarCoderBase-1.1B,1.1,5.46,71.4,8192,86,15.17,14.2,13.38,11.68,9.94,11.31,4.65,9.81,12.52,5.73,5.03,10.24,3.92,2360.0,4586,StarCoderBase-1.1B,https://huggingface.co/bigcode/starcoderbase-1b
-🟢,CodeGen25-7B-mono,7.0,5.46,34.1,2048,86,33.08,19.75,23.22,18.62,16.75,4.65,4.32,12.1,6.75,4.41,4.07,7.83,1.71,687.0,15336,CodeGen25-7B-mono,https://huggingface.co/Salesforce/codegen25-7b-mono
-🟢,CodeGen-16B-Multi,16.0,5.19,17.2,2048,6,19.26,22.2,19.15,21.0,8.37,0.0,7.68,9.89,8.5,6.45,0.66,4.21,1.25,0.0,32890,CodeGen-16B-Multi,https://huggingface.co/Salesforce/codegen-16B-multi
-🟢,StableCode-3B,3.0,3.81,30.2,16384,7,20.2,19.54,18.98,20.77,3.95,0.0,4.77,8.1,5.14,0.8,0.008,2.03,0.98,718.0,15730,StableCode-3B,https://huggingface.co/stabilityai/stablecode-completion-alpha-3b
-🟢,DeciCoder-1B,1.0,3.5,54.6,2048,3,19.32,15.3,17.85,6.87,2.01,0.0,6.08,5.86,0.0,0.1,0.47,1.72,0.63,2490.0,4436,DeciCoder-1B,
-🟢,SantaCoder-1.1B,1.1,2.5,50.8,2048,3,18.12,15.0,15.47,6.2,1.5,0.0,0.0,4.92,0.1,0.0,0.0,2.0,0.7,2270.0,4602,SantaCoder-1.1B,https://huggingface.co/bigcode/santacoder
+🔶,CodeLlama-34b-Instruct,34.0,22.69,15.1,16384,UNK,50.79,41.53,45.85,41.53,36.98,32.65,13.63,35.09,38.87,24.25,18.09,39.26,37.63,0.0,69957,CodeLlama-34b-Instruct,https://huggingface.co/codellama/CodeLlama-34b-Instruct-hf
+🟢,CodeLlama-34b,34.0,22.0,15.1,16384,UNK,45.11,40.19,41.66,41.42,40.43,31.4,15.27,33.89,37.49,22.71,16.94,38.73,35.28,0.0,69957,CodeLlama-34b,https://huggingface.co/codellama/CodeLlama-34b-hf
+🟢,CodeLlama-34b-Python,34.0,21.54,15.1,16384,UNK,53.29,39.46,44.72,39.09,39.78,31.37,17.29,33.87,31.9,22.35,13.19,39.67,34.3,0.0,69957,CodeLlama-34b-Python,https://huggingface.co/codellama/CodeLlama-34b-Python-hf
+🔶,WizardCoder-15B-V1.0,15.0,21.23,43.7,8192,86,58.12,35.77,41.91,38.95,39.34,33.98,12.14,32.07,27.85,22.53,13.39,33.74,27.06,1470.0,32414,WizardCoder-15B-V1.0,https://huggingface.co/WizardLM/WizardCoder-15B-V1.0
+🔶,CodeLlama-13b-Instruct,13.0,20.23,25.3,16384,UNK,50.6,33.99,40.92,36.36,32.07,32.23,16.29,31.29,31.6,20.14,16.66,32.82,31.75,0.0,28568,CodeLlama-13b-Instruct,https://huggingface.co/codellama/CodeLlama-13b-Instruct-hf
+🟢,CodeLlama-13b,13.0,18.69,25.3,16384,UNK,35.07,32.23,38.26,35.81,32.57,28.01,15.78,28.35,31.26,18.32,13.63,29.72,29.54,0.0,28568,CodeLlama-13b,https://huggingface.co/codellama/CodeLlama-13b-hf
+🟢,CodeLlama-13b-Python,13.0,17.77,25.3,16384,UNK,42.89,33.56,40.66,36.21,34.55,30.4,9.82,28.67,29.9,18.35,12.51,29.32,25.85,0.0,28568,CodeLlama-13b-Python,https://huggingface.co/codellama/CodeLlama-13b-Python-hf
+🔶,CodeLlama-7b-Instruct,7.0,16.69,33.1,16384,UNK,45.65,28.77,33.11,29.03,28.55,27.58,11.81,26.45,30.47,19.7,11.81,24.27,26.66,693.0,15853,CodeLlama-7b-Instruct,https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf
+🟢,CodeLlama-7b,7.0,15.54,33.1,16384,UNK,29.98,29.2,31.8,27.23,25.17,25.6,11.6,24.36,30.36,18.04,11.94,25.82,25.52,693.0,15853,CodeLlama-7b,https://huggingface.co/codellama/CodeLlama-7b-hf
+🔶,OctoCoder-15B,15.0,14.85,44.4,8192,86,45.3,26.03,32.8,29.32,26.76,24.5,13.35,24.01,22.56,14.39,10.61,24.26,18.24,1520.0,32278,OctoCoder-15B,https://huggingface.co/bigcode/octocoder
+🟢,StarCoder-15B,15.0,14.58,43.9,8192,86,33.57,30.22,30.79,31.55,26.08,23.02,13.57,22.74,23.89,15.5,0.07,21.84,22.74,1490.0,33461,StarCoder-15B,https://huggingface.co/bigcode/starcoder
+🟢,CodeLlama-7b-Python,7.0,14.46,33.1,16384,UNK,40.48,29.15,36.34,30.34,1.08,28.53,8.94,23.5,26.15,18.25,9.04,26.96,26.75,693.0,15853,CodeLlama-7b-Python,https://huggingface.co/codellama/CodeLlama-7b-Python-hf
+🟢,StarCoderBase-15B,15.0,14.15,43.8,8192,86,30.35,28.53,31.7,30.56,26.75,21.09,10.01,22.4,26.61,10.18,11.77,24.46,16.74,1460.0,32366,StarCoderBase-15B,https://huggingface.co/bigcode/starcoderbase
+🟢,CodeGeex2-6B,6.0,11.96,32.7,8192,100,33.49,23.46,29.9,28.45,25.27,20.93,8.44,21.23,15.94,14.58,11.75,20.45,22.06,982.0,14110,CodeGeex2-6B,https://huggingface.co/THUDM/codegeex2-6b
+🟢,StarCoderBase-7B,7.0,11.77,46.9,8192,86,28.37,24.44,27.35,23.3,22.12,21.77,8.1,20.17,23.35,14.51,11.08,22.6,15.1,1700.0,16512,StarCoderBase-7B,https://huggingface.co/bigcode/starcoderbase-7b
+🔶,OctoGeeX-7B,7.0,11.65,32.7,8192,100,42.28,19.33,28.5,23.93,25.85,22.94,9.77,20.79,16.19,13.66,12.02,17.94,17.03,982.0,14110,OctoGeeX-7B,https://huggingface.co/bigcode/octogeex
+🟢,CodeGen25-7B-multi,7.0,10.42,32.6,2048,86,28.7,26.01,26.27,25.75,21.98,19.11,8.84,20.04,23.44,11.59,10.37,21.84,16.62,680.0,15336,CodeGen25-7B-multi,https://huggingface.co/Salesforce/codegen25-7b-multi
+🟢,StarCoderBase-3B,3.0,8.54,50.0,8192,86,21.5,19.25,21.32,19.43,18.55,16.1,4.97,15.29,18.04,10.1,7.87,16.32,9.98,1770.0,8414,StarCoderBase-3B,https://huggingface.co/bigcode/starcoderbase-3b
+🟢,Replit-2.7B,2.7,6.38,42.2,2048,20,20.12,21.39,20.18,20.37,16.14,1.24,6.41,11.62,2.11,7.2,3.22,15.19,5.88,577.0,7176,Replit-2.7B,https://huggingface.co/replit/replit-code-v1-3b
+🟢,StarCoderBase-1.1B,1.1,6.23,71.4,8192,86,15.17,14.2,13.38,11.68,9.94,11.31,4.65,9.81,12.52,5.73,5.03,10.24,3.92,2360.0,4586,StarCoderBase-1.1B,https://huggingface.co/bigcode/starcoderbase-1b
+🟢,CodeGen25-7B-mono,7.0,6.0,34.1,2048,86,33.08,19.75,23.22,18.62,16.75,4.65,4.32,12.1,6.75,4.41,4.07,7.83,1.71,687.0,15336,CodeGen25-7B-mono,https://huggingface.co/Salesforce/codegen25-7b-mono
+🟢,CodeGen-16B-Multi,16.0,5.5,17.2,2048,6,19.26,22.2,19.15,21.0,8.37,0.0,7.68,9.89,8.5,6.45,0.66,4.21,1.25,0.0,32890,CodeGen-16B-Multi,https://huggingface.co/Salesforce/codegen-16B-multi
+🟢,StableCode-3B,3.0,4.58,30.2,16384,7,20.2,19.54,18.98,20.77,3.95,0.0,4.77,8.1,5.14,0.8,0.008,2.03,0.98,718.0,15730,StableCode-3B,https://huggingface.co/stabilityai/stablecode-completion-alpha-3b
+🟢,DeciCoder-1B,1.0,4.27,54.6,2048,3,19.32,15.3,17.85,6.87,2.01,0.0,6.08,5.86,0.0,0.1,0.47,1.72,0.63,2490.0,4436,DeciCoder-1B,
+🟢,SantaCoder-1.1B,1.1,3.27,50.8,2048,3,18.12,15.0,15.47,6.2,1.5,0.0,0.0,4.92,0.1,0.0,0.0,2.0,0.7,2270.0,4602,SantaCoder-1.1B,https://huggingface.co/bigcode/santacoder

data/raw_scores.csv

@@ -1,17 +1,26 @@
-Models,Size (B),Throughput (tokens/s),Seq_length,#Languages,humaneval-python,java,javascript,cpp,php,julia,d,lua,r,racket,rust,swift,Throughput (tokens/s) bs=50,Peak Memory (MB)
-CodeGen-16B-Multi,16.0,17.2,2048,6,19.26,22.2,19.15,21.0,8.37,0.0,7.68,8.5,6.45,0.66,4.21,1.25,0.0,32890
-StarCoder-15B,15.0,43.9,8192,86,33.57,30.22,30.79,31.55,26.08,23.02,13.57,23.89,15.5,0.07,21.84,22.74,1490.0,33461
-StarCoderBase-15B,15.0,43.8,8192,86,30.35,28.53,31.7,30.56,26.75,21.09,10.01,26.61,10.18,11.77,24.46,16.74,1460.0,32366
-StarCoderBase-7B,7.0,46.9,8192,86,28.37,24.44,27.35,23.3,22.12,21.77,8.1,23.35,14.51,11.08,22.6,15.1,1700.0,16512
-StarCoderBase-3B,3.0,50.0,8192,86,21.5,19.25,21.32,19.43,18.55,16.1,4.97,18.04,10.1,7.87,16.32,9.98,1770.0,8414
-Replit-2.7B,2.7,42.2,2048,20,20.12,21.39,20.18,20.37,16.14,1.24,6.41,2.11,7.2,3.22,15.19,5.88,577.0,7176
-SantaCoder-1.1B,1.1,50.8,2048,3,18.12,15.0,15.47,6.2,1.5,0.0,0.0,0.1,0.0,0.0,2.0,0.7,2270.0,4602
-StarCoderBase-1.1B,1.1,71.4,8192,86,15.17,14.2,13.38,11.68,9.94,11.31,4.65,12.52,5.73,5.03,10.24,3.92,2360.0,4586
-CodeGen25-7B-mono,7.0,34.1,2048,86,33.08,19.75,23.22,18.62,16.75,4.65,4.32,6.75,4.41,4.07,7.83,1.71,687.0,15336
-CodeGen25-7B-multi,7.0,32.6,2048,86,28.7,26.01,26.27,25.75,21.98,19.11,8.84,23.44,11.59,10.37,21.84,16.62,680.0,15336
-CodeGeex2-6B,6.0,32.7,8192,100,33.49,23.46,29.9,28.45,25.27,20.93,8.44,15.94,14.58,11.75,20.45,22.06,982,14110
-WizardCoder-15B-V1.0,15.0,43.7,8192,86,58.12,35.77,41.91,38.95,39.34,33.98,12.14,27.85,22.53,13.39,33.74,27.06,1470.0,32414
-StableCode-3B,3,30.2,16384,7,20.2,19.54,18.98,20.77,3.95,0,4.77,5.14,0.8,0.008,2.03,0.98,718,15730
-OctoCoder-15B,15,44.4,8192,86,45.3,26.03,32.8,29.32,26.76,24.5,13.35,22.56,14.39,10.61,24.26,18.24,1520,32278
-OctoGeeX-7B,7,32.7,8192,100,42.28,19.33,28.5,23.93,25.85,22.94,9.77,16.19,13.66,12.02,17.94,17.03,982,14110
-DeciCoder-1B,1,54.60,2048,3,19.32,15.3,17.85,6.87,2.01,0.0,6.08,0.0,0.1,0.47,1.72,0.63,2490,4436
+Models,Size (B),Throughput (tokens/s),Seq_length,#Languages,humaneval-python,java,javascript,cpp,php,julia,d,lua,r,racket,rust,swift,Throughput (tokens/s) bs=50,Peak Memory (MB)
+CodeGen-16B-Multi,16.0,17.2,2048,6,19.26,22.2,19.15,21.0,8.37,0.0,7.68,8.5,6.45,0.66,4.21,1.25,0.0,32890
+StarCoder-15B,15.0,43.9,8192,86,33.57,30.22,30.79,31.55,26.08,23.02,13.57,23.89,15.5,0.07,21.84,22.74,1490.0,33461
+StarCoderBase-15B,15.0,43.8,8192,86,30.35,28.53,31.7,30.56,26.75,21.09,10.01,26.61,10.18,11.77,24.46,16.74,1460.0,32366
+StarCoderBase-7B,7.0,46.9,8192,86,28.37,24.44,27.35,23.3,22.12,21.77,8.1,23.35,14.51,11.08,22.6,15.1,1700.0,16512
+StarCoderBase-3B,3.0,50.0,8192,86,21.5,19.25,21.32,19.43,18.55,16.1,4.97,18.04,10.1,7.87,16.32,9.98,1770.0,8414
+Replit-2.7B,2.7,42.2,2048,20,20.12,21.39,20.18,20.37,16.14,1.24,6.41,2.11,7.2,3.22,15.19,5.88,577.0,7176
+SantaCoder-1.1B,1.1,50.8,2048,3,18.12,15.0,15.47,6.2,1.5,0.0,0.0,0.1,0.0,0.0,2.0,0.7,2270.0,4602
+StarCoderBase-1.1B,1.1,71.4,8192,86,15.17,14.2,13.38,11.68,9.94,11.31,4.65,12.52,5.73,5.03,10.24,3.92,2360.0,4586
+CodeGen25-7B-mono,7.0,34.1,2048,86,33.08,19.75,23.22,18.62,16.75,4.65,4.32,6.75,4.41,4.07,7.83,1.71,687.0,15336
+CodeGen25-7B-multi,7.0,32.6,2048,86,28.7,26.01,26.27,25.75,21.98,19.11,8.84,23.44,11.59,10.37,21.84,16.62,680.0,15336
+CodeGeex2-6B,6.0,32.7,8192,100,33.49,23.46,29.9,28.45,25.27,20.93,8.44,15.94,14.58,11.75,20.45,22.06,982,14110
+WizardCoder-15B-V1.0,15.0,43.7,8192,86,58.12,35.77,41.91,38.95,39.34,33.98,12.14,27.85,22.53,13.39,33.74,27.06,1470.0,32414
+StableCode-3B,3,30.2,16384,7,20.2,19.54,18.98,20.77,3.95,0,4.77,5.14,0.8,0.008,2.03,0.98,718,15730
+OctoCoder-15B,15,44.4,8192,86,45.3,26.03,32.8,29.32,26.76,24.5,13.35,22.56,14.39,10.61,24.26,18.24,1520,32278
+OctoGeeX-7B,7,32.7,8192,100,42.28,19.33,28.5,23.93,25.85,22.94,9.77,16.19,13.66,12.02,17.94,17.03,982,14110
+DeciCoder-1B,1,54.60,2048,3,19.32,15.3,17.85,6.87,2.01,0.0,6.08,0.0,0.1,0.47,1.72,0.63,2490,4436
+CodeLlama-7b,7,33.10,16384,UNK,29.98,29.2,31.8,27.23,25.17,25.6,11.6,30.36,18.04,11.94,25.82,25.52,693,15853
+CodeLlama-7b-Python,7,33.10,16384,UNK,40.48,29.15,36.34,30.34,1.08,28.53,8.94,26.15,18.25,9.04,26.96,26.75,693,15853
+CodeLlama-7b-Instruct,7,33.10,16384,UNK,45.65,28.77,33.11,29.03,28.55,27.58,11.81,30.47,19.7,11.81,24.27,26.66,693,15853
+CodeLlama-13b,13,25.30,16384,UNK,35.07,32.23,38.26,35.81,32.57,28.01,15.78,31.26,18.32,13.63,29.72,29.54,0,28568
+CodeLlama-13b-Python,13,25.30,16384,UNK,42.89,33.56,40.66,36.21,34.55,30.4,9.82,29.9,18.35,12.51,29.32,25.85,0,28568
+CodeLlama-13b-Instruct,13,25.30,16384,UNK,50.60,33.99,40.92,36.36,32.07,32.23,16.29,31.6,20.14,16.66,32.82,31.75,0,28568
+CodeLlama-34b,34,15.10,16384,UNK,45.11,40.19,41.66,41.42,40.43,31.4,15.27,37.49,22.71,16.94,38.73,35.28,0,69957
+CodeLlama-34b-Python,34,15.10,16384,UNK,53.29,39.46,44.72,39.09,39.78,31.37,17.29,31.9,22.35,13.19,39.67,34.3,0,69957
+CodeLlama-34b-Instruct,34,15.10,16384,UNK,50.79,41.53,45.85,41.53,36.98,32.65,13.63,38.87,24.25,18.09,39.26,37.63,0,69957

src/add_json_csv.py

@@ -0,0 +1,49 @@
+import csv
+import json
+
+# Given mapping
+mapping = {
+    "humaneval": "humaneval-python",
+    "multiple-lua": "lua",
+    "multiple-java": "java",
+    "multiple-jl": "julia",
+    "multiple-cpp": "cpp",
+    "multiple-rs": "rust",
+    "multiple-rkt": "racket",
+    "multiple-php": "php",
+    "multiple-r": "r",
+    "multiple-js": "javascript",
+    "multiple-d": "d",
+    "multiple-swift": "swift"
+}
+
+# JSON Data (replace this with your actual loaded JSON)
+json_path = "/fsx/loubna/code/dev/leader/bigcode-evaluation-harness/codellama_CodeLlama-13b-Instruct-hf_loubnabnl.json"
+with open(json_path, "r") as f:
+    json_data = json.load(f)
+parsed_data = json_data['results']
+
+# Create a dictionary with column names as keys and empty values
+csv_columns = ["Models", "Size (B)", "Throughput (tokens/s)", "Seq_length", "#Languages", "humaneval-python", "java", "javascript", "cpp", "php", "julia", "d", "lua", "r", "racket", "rust", "swift", "Throughput (tokens/s) bs=50", "Peak Memory (MB)"]
+row_data = {col: '' for col in csv_columns}
+
+# Fill the dictionary with data from the JSON
+for item in parsed_data:
+    csv_col = mapping.get(item['task'])
+    if csv_col:
+        row_data[csv_col] = round(item['pass@1'] * 100, 2)
+
+# Set model name under the 'Models' column
+row_data['Models'] = json_data['meta']['model']
+
+# Write to CSV
+csv_file = "/fsx/loubna/internal-code-leaderboard/data/raw_scores.csv"
+with open(csv_file, 'a', newline='') as csvfile:
+    writer = csv.DictWriter(csvfile, fieldnames=row_data.keys())
+    writer.writerow(row_data)
+
+# print last 3 rows in csv
+with open(csv_file, 'r') as f:
+    lines = f.readlines()
+    for line in lines[-3:]:
+        print(line)

src/build.py

@@ -45,10 +45,14 @@ links = {
     "CodeGen-16B-Multi": "https://huggingface.co/Salesforce/codegen-16B-multi",
     "Deci/DeciCoder-1b": "https://huggingface.co/Deci/DeciCoder-1b",
 }
+codellamas = ['CodeLlama-7b', 'CodeLlama-7b-Python', 'CodeLlama-7b-Instruct', 'CodeLlama-13b', 'CodeLlama-13b-Python', 'CodeLlama-13b-Instruct', 'CodeLlama-34b', 'CodeLlama-34b-Python', 'CodeLlama-34b-Instruct']
+for codellama in codellamas:
+    links[codellama] = f"https://huggingface.co/codellama/{codellama}-hf"
+
 df["Links"] = df["Models"].map(links)
 
 df.insert(0, "T", "🟢")
-df.loc[(df["Models"].str.contains("WizardCoder") | df["Models"].str.contains("Octo")), "T"] = "🔶"
+df.loc[(df["Models"].str.contains("WizardCoder") | df["Models"].str.contains("Octo") | df["Models"].str.contains("Instruct")), "T"] = "🔶"
 # print first 5 rows and 10 cols
 print(df.iloc[:5, :-1])
 df.to_csv("data/code_eval_board.csv", index=False)

src/utils.py

@@ -66,12 +66,13 @@ def plot_throughput(df, bs=1):
     df.loc[df["Models"].str.contains("StarCoder|SantaCoder"), "color"] = "orange"
     df.loc[df["Models"].str.contains("CodeGen"), "color"] = "pink"
     df.loc[df["Models"].str.contains("Replit"), "color"] = "purple"
-    df.loc[df["Models"].str.contains("WizardCoder"), "color"] = "green"
+    df.loc[df["Models"].str.contains("WizardCoder"), "color"] = "peru"
     df.loc[df["Models"].str.contains("CodeGeex"), "color"] = "cornflowerblue"
     df.loc[df["Models"].str.contains("StableCode"), "color"] = "cadetblue"
     df.loc[df["Models"].str.contains("OctoCoder"), "color"] = "lime"
     df.loc[df["Models"].str.contains("OctoGeeX"), "color"] = "wheat"
     df.loc[df["Models"].str.contains("Deci"), "color"] = "salmon"
+    df.loc[df["Models"].str.contains("CodeLlama"), "color"] = "palevioletred"
 
     fig = go.Figure()