Hugging Face's logo

codefuse-ai
/
CodeFuse-DeepSeek-33B

Text Generation
Transformers
PyTorch
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
8
codefuse-admin commited on
Commit
4163e84
•
1 Parent(s): b5959bb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -10
README.md CHANGED
@@ -53,8 +53,8 @@ CodeFuse-DeepSeek-33B is a 33B Code-LLM finetuned by QLoRA on multiple code-rela
53
 
54
  | Model | HumanEval(pass@1) | Date |
55
  |:----------------------------|:-----------------:|:-------:|
56
- | **CodeFuse-CodeLlama-34B** | **74.4%** | 2023.9 |
57
- |**CodeFuse-CodeLlama-34B-4bits** | **73.8%** | 2023.9 |
58
  | WizardCoder-Python-34B-V1.0 | 73.2% | 2023.8 |
59
  | GPT-4(zero-shot) | 67.0% | 2023.3 |
60
  | PanGu-Coder2 15B | 61.6% | 2023.8 |
@@ -64,9 +64,9 @@ CodeFuse-DeepSeek-33B is a 33B Code-LLM finetuned by QLoRA on multiple code-rela
64
  | OctoCoder | 46.2% | 2023.8 |
65
  | StarCoder-15B | 33.6% | 2023.5 |
66
  | Qwen-14b | 32.3% | 2023.10 |
67
- | **CodeFuse-StarCoder-15B** | **54.9%** | 2023.9 |
68
- | **CodeFuse-QWen-14B** | **48.78%** | 2023.10 |
69
- | **CodeFuse-CodeGeeX2-6B** | **45.12%** | 2023.11 |
70
  | **CodeFuse-DeepSeek-33B** | **78.65%** | 2024.01 |
71
 
72
 
@@ -220,8 +220,8 @@ CodeFuse-DeepSeek-33B 是一个通过QLoRA对基座模型DeepSeek-Coder-33B进
220
 
221
  | 模型 | HumanEval(pass@1) | 日期 |
222
  |:----------------------------|:-----------------:|:-------:|
223
- | **CodeFuse-CodeLlama-34B** | **74.4%** | 2023.9 |
224
- |**CodeFuse-CodeLlama-34B-4bits** | **73.8%** | 2023.9 |
225
  | WizardCoder-Python-34B-V1.0 | 73.2% | 2023.8 |
226
  | GPT-4(zero-shot) | 67.0% | 2023.3 |
227
  | PanGu-Coder2 15B | 61.6% | 2023.8 |
@@ -231,9 +231,9 @@ CodeFuse-DeepSeek-33B 是一个通过QLoRA对基座模型DeepSeek-Coder-33B进
231
  | OctoCoder | 46.2% | 2023.8 |
232
  | StarCoder-15B | 33.6% | 2023.5 |
233
  | Qwen-14b | 32.3% | 2023.10 |
234
- | **CodeFuse-StarCoder-15B** | **54.9%** | 2023.9 |
235
- | **CodeFuse-QWen-14B** | **48.78%** | 2023.8 |
236
- | **CodeFuse-CodeGeeX2-6B** | **45.12%** | 2023.11 |
237
  | **CodeFuse-DeepSeek-33B**. | **78.65%** | 2024.01 |
238
 
239
 
 
53
 
54
  | Model | HumanEval(pass@1) | Date |
55
  |:----------------------------|:-----------------:|:-------:|
56
+ | **CodeFuse-CodeLlama-34B** | 74.4% | 2023.9 |
57
+ |**CodeFuse-CodeLlama-34B-4bits** | 73.8% | 2023.9 |
58
  | WizardCoder-Python-34B-V1.0 | 73.2% | 2023.8 |
59
  | GPT-4(zero-shot) | 67.0% | 2023.3 |
60
  | PanGu-Coder2 15B | 61.6% | 2023.8 |
 
64
  | OctoCoder | 46.2% | 2023.8 |
65
  | StarCoder-15B | 33.6% | 2023.5 |
66
  | Qwen-14b | 32.3% | 2023.10 |
67
+ | **CodeFuse-StarCoder-15B** | 54.9% | 2023.9 |
68
+ | **CodeFuse-QWen-14B** | 48.78% | 2023.10 |
69
+ | **CodeFuse-CodeGeeX2-6B** | 45.12% | 2023.11 |
70
  | **CodeFuse-DeepSeek-33B** | **78.65%** | 2024.01 |
71
 
72
 
 
220
 
221
  | 模型 | HumanEval(pass@1) | 日期 |
222
  |:----------------------------|:-----------------:|:-------:|
223
+ | **CodeFuse-CodeLlama-34B** | 74.4% | 2023.9 |
224
+ |**CodeFuse-CodeLlama-34B-4bits** | 73.8% | 2023.9 |
225
  | WizardCoder-Python-34B-V1.0 | 73.2% | 2023.8 |
226
  | GPT-4(zero-shot) | 67.0% | 2023.3 |
227
  | PanGu-Coder2 15B | 61.6% | 2023.8 |
 
231
  | OctoCoder | 46.2% | 2023.8 |
232
  | StarCoder-15B | 33.6% | 2023.5 |
233
  | Qwen-14b | 32.3% | 2023.10 |
234
+ | **CodeFuse-StarCoder-15B** | 54.9% | 2023.9 |
235
+ | **CodeFuse-QWen-14B** | 48.78% | 2023.8 |
236
+ | **CodeFuse-CodeGeeX2-6B** | 45.12% | 2023.11 |
237
  | **CodeFuse-DeepSeek-33B**. | **78.65%** | 2024.01 |
238
 
239