From 15ec4d27e55f48c8d9663839269f7f8fd077e3de Mon Sep 17 00:00:00 2001 From: Daya Guo <40300434+guoday@users.noreply.github.com> Date: Sun, 29 Oct 2023 14:45:24 +0800 Subject: [PATCH] Update README_zh.md --- README_zh.md | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/README_zh.md b/README_zh.md index 8c80544..fdf5709 100644 --- a/README_zh.md +++ b/README_zh.md @@ -1,7 +1,7 @@

DeepSeek Coder

-

[主页] | [🤖 在线体验] | [🤗 模型下载] | [📄 English Version]

+

[主页] | [🤖 在线体验] | [🤗 模型下载] | [📄 English Version]

@@ -224,7 +224,7 @@ print(tokenizer.decode(outputs[0])) #### 1) [HumanEval](https://github.com/deepseek-ai/deepseek-coder/tree/main/Evaluation/HumanEval) -##### Multilingual Base Models +Multilingual Base Models | Model | Size | Python | C++ | Java | PHP | TS | C# | Bash | JS | Avg | | ------------------- | ---- | ------ | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | @@ -232,15 +232,15 @@ print(tokenizer.decode(outputs[0])) | CodeShell | 7B | 35.4% | 32.9% | 34.2% | 31.7% | 30.2% | 38.0% | 7.0% | 33.5% | 30.4% | | CodeGeeX2 | 6B | 36.0% | 29.2% | 25.9% | 23.6% | 20.8% | 29.7% | 6.3% | 24.8% | 24.5% | | StarCoderBase | 16B | 31.7% | 31.1% | 28.5% | 25.4% | 34.0% | 34.8% | 8.9% | 29.8% | 28.0% | -| CodeLLama (7B) | 7B | 31.7% | 29.8% | 34.2% | 23.6% | 36.5% | 36.7% | 12.0% | 29.2% | 29.2% | -| CodeLLama (13B) | 13B | 36.0% | 37.9% | 38.0% | 34.2% | 45.2% | 43.0% | 16.5% | 32.3% | 35.4% | -| CodeLLama (34B) | 34B | 48.2% | 44.7% | 44.9% | 41.0% | 42.1% | 48.7% | 15.8% | 42.2% | 41.0% | +| CodeLLama | 7B | 31.7% | 29.8% | 34.2% | 23.6% | 36.5% | 36.7% | 12.0% | 29.2% | 29.2% | +| CodeLLama | 13B | 36.0% | 37.9% | 38.0% | 34.2% | 45.2% | 43.0% | 16.5% | 32.3% | 35.4% | +| CodeLLama | 34B | 48.2% | 44.7% | 44.9% | 41.0% | 42.1% | 48.7% | 15.8% | 42.2% | 41.0% | | | | | | | | | | | | | -| OraCoder-Base (1B) | 1B | 34.8% | 31.1% | 32.3% | 24.2% | 28.9% | 36.7% | 10.1% | 28.6% | 28.3% | -| OraCoder-Base (7B) | 7B | 49.4% | 50.3% | 43.0% | 38.5% | 49.7% | 50.0% | 28.5% | 48.4% | 44.7% | -| OraCoder-Base (33B) | 33B | - | - | - | - | - | - | - | - | - | +| DeepSeek-Coder-Base | 1B | 34.8% | 31.1% | 32.3% | 24.2% | 28.9% | 36.7% | 10.1% | 28.6% | 28.3% | +| DeepSeek-Coder-Base | 7B | 49.4% | 50.3% | 43.0% | 38.5% | 49.7% | 50.0% | 28.5% | 48.4% | 44.7% | +| DeepSeek-Coder-Base | 33B | - | - | - | - | - | - | - | - | - | -##### Instruction-Tuned Models +Instruction-Tuned Models | Model | Size | Python | C++ | Java | PHP | TS | C# | Bash | JS | Avg | | ------------------- | ---- | ------ | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | | ChatGPT | - | 70.7% | 50.3% | 54.5% | 52.2% | 62.3% | 64.6% | 34.8% | 60.9% | 52.2% | @@ -248,15 +248,15 @@ print(tokenizer.decode(outputs[0])) | WizardCoder | 16B | 51.8% | 41.6% | 41.1% | 42.2% | 44.7% | 46.8% | 12.7% | 42.8% | 40.5% | | Phind-CodeLlama | 34B | - | - | - | - | - | - | - | - | - | | | | | | | | | | | | | -| OraCoder-Chat (1B) | 1B | - | - | - | - | - | - | - | - | - | -| OraCoder-Chat (7B) | 7B | - | - | - | - | - | - | - | - | - | -| OraCoder-Chat (33B) | 33B | - | - | - | - | - | - | - | - | - | +| DeepSeek-Coder-Instruct | 1B | - | - | - | - | - | - | - | - | - | +| DeepSeek-Coder-Instruct | 7B | - | - | - | - | - | - | - | - | - | +| DeepSeek-Coder-Instruct | 33B | - | - | - | - | - | - | - | - | - | #### 2) [Math Reasoning](https://github.com/deepseek-ai/deepseek-coder/tree/main/Evaluation/PAL-Math) -##### Multilingual Base Models +Multilingual Base Models | Model | Size | GSM8k | MATH | GSM-Hard | SVAMP | TabMWP | ASDiv | MAWPS | Avg | | -------------- | ---- | ----- | ----- | -------- | ----- | ------ | ----- | ----- | ----- | @@ -267,20 +267,20 @@ print(tokenizer.decode(outputs[0])) | CodeLLama-Base | 13B | 44.2% | 15.5% | 42.4% | 65.6% | 61.6% | 65.3% | 85.3% | 54.3% | | CodeLLama-Base | 34B | 58.2% | 22.1% | 55.2% | 77.2% | 69.6% | 70.0% | 92.8% | 63.6% | | | | | | | | | | | | -| OraCoder-Base | 1B | 17.0% | 13.4% | 13.3% | 39.2% | 42.4% | 44.8% | 66.0% | 33.7% | -| OraCoder-Base | 7B | 46.0% | 20.6% | 40.0% | 67.2% | 71.2% | 67.1% | 89.1% | 57.3% | -| OraCoder-Base | 33B | - | - | - | - | - | - | - | - | +| DeepSeek-Coder-Base | 1B | 17.0% | 13.4% | 13.3% | 39.2% | 42.4% | 44.8% | 66.0% | 33.7% | +| DeepSeek-Coder-Base | 7B | 46.0% | 20.6% | 40.0% | 67.2% | 71.2% | 67.1% | 89.1% | 57.3% | +| DeepSeek-Coder-Base | 33B | - | - | - | - | - | - | - | - | -##### Instruction-Tuned Models +Instruction-Tuned Models | Model | Size | GSM8k | MATH | GSM-Hard | SVAMP | TabMWP | ASDiv | MAWPS | Avg | | ------------- | ---- | ----- | ----- | -------- | ----- | ------ | ----- | ----- | ----- | | ChatGPT | - | 78.6% | 38.7% | 67.6% | 77.8% | 79.9% | 81.0% | 89.4% | 73.3% | | GPT-4 | - | 94.2% | 51.8% | 77.6% | 94.8% | 95.9% | 92.6% | 97.7% | 86.4% | | | | | | | | | | | | -| OraCoder-Chat | 1B | - | - | - | - | - | - | - | - | -| OraCoder-Chat | 7B | - | - | - | - | - | - | - | - | -| OraCoder-Chat | 33B | - | - | - | - | - | - | - | - | +| DeepSeek-Coder-Instruct | 1B | - | - | - | - | - | - | - | - | +| DeepSeek-Coder-Instruct | 7B | - | - | - | - | - | - | - | - | +| DeepSeek-Coder-Instruct | 33B | - | - | - | - | - | - | - | - | ### 6. 协议