FredZhang7 commited on
Commit
b03b089
·
verified ·
1 Parent(s): 512cf62

add license notice

Browse files
Files changed (1) hide show
  1. README.md +11 -3
README.md CHANGED
@@ -46,9 +46,9 @@ Think step by step. Solve this problem without removing any existing functionali
46
  | 2 | Claude-3.5-Sonnet | N/A | Poor in complex debugging compared to Codestral | Excellent, better than GPT-4o in long code generation | Great for code generation, but weaker in debugging. |
47
  | 3 | GPT-4o | N/A | Good at complex debugging but can be outperformed by Codestral | Excellent, generally reliable for code generation | Balanced performance between code debugging and generation. |
48
  | 4 | DeepSeekV2 Coder Instruct | N/A | Poor, outputs the same code in complex scenarios | Great at general code generation, rivals GPT-4o | Excellent at code generation, but has data privacy concerns as per Privacy Policy. |
49
- | 5 | qwen2 7b instruct bf16 | 78.22 | Average, can think of correct approaches | Sometimes helps generate new ideas | High speed, useful for generating ideas. |
50
- | 6 | GPT-4o-mini | N/A | Decent, but struggles with complex debugging tasks | Reliable for shorter or simpler code generation tasks | Suitable for less complex coding tasks. |
51
- | 7 | AutoCoder.IQ4_K.gguf | 26.43 | Average, offers different approaches but can be incorrect | Generates useful short code segments | Use Precise Mode for better results. |
52
  | 8 | Meta-Llama-3.1-70B-Instruct-IQ2_XS.gguf | 2.55 | Poor, too slow to be practical in day-to-day workflows | Occasionally helps generate ideas | Speed is a significant limitation. |
53
  | 9 | Trinity-2-Codestral-22B-Q6_K_L | N/A | Poor, similar issues to DeepSeekV2 in outputing the same code | Decent, but often repeats code | Similar problem to DeepSeekV2, not recommended for my complex tasks. |
54
  | 10 | DeepSeekV2 Coder Lite Instruct Q_8L | N/A | Poor, repeats code similar to other models in its family | Not as effective in my context | Not recommended overall based on my criteria. |
@@ -107,6 +107,14 @@ The following are tested in my workflow, but may not generalize well to other wo
107
 
108
  <br>
109
 
 
 
 
 
 
 
 
 
110
  ## Download
111
 
112
  ```
 
46
  | 2 | Claude-3.5-Sonnet | N/A | Poor in complex debugging compared to Codestral | Excellent, better than GPT-4o in long code generation | Great for code generation, but weaker in debugging. |
47
  | 3 | GPT-4o | N/A | Good at complex debugging but can be outperformed by Codestral | Excellent, generally reliable for code generation | Balanced performance between code debugging and generation. |
48
  | 4 | DeepSeekV2 Coder Instruct | N/A | Poor, outputs the same code in complex scenarios | Great at general code generation, rivals GPT-4o | Excellent at code generation, but has data privacy concerns as per Privacy Policy. |
49
+ | 5* | Qwen2-7b-Instruct bf16 | 78.22 | Average, can think of correct approaches | Sometimes helps generate new ideas | High speed, useful for generating ideas. |
50
+ | 5* | AutoCoder.IQ4_K.gguf | 26.43 | Excellent at solutions that require one to few lines of edits | Generates useful short code segments | Use Precise Mode for better results. |
51
+ | 7 | GPT-4o-mini | N/A | Decent, but struggles with complex debugging tasks | Reliable for shorter or simpler code generation tasks | Suitable for less complex coding tasks. |
52
  | 8 | Meta-Llama-3.1-70B-Instruct-IQ2_XS.gguf | 2.55 | Poor, too slow to be practical in day-to-day workflows | Occasionally helps generate ideas | Speed is a significant limitation. |
53
  | 9 | Trinity-2-Codestral-22B-Q6_K_L | N/A | Poor, similar issues to DeepSeekV2 in outputing the same code | Decent, but often repeats code | Similar problem to DeepSeekV2, not recommended for my complex tasks. |
54
  | 10 | DeepSeekV2 Coder Lite Instruct Q_8L | N/A | Poor, repeats code similar to other models in its family | Not as effective in my context | Not recommended overall based on my criteria. |
 
107
 
108
  <br>
109
 
110
+ ## License
111
+
112
+ A reminder that Codestral 22b should only be used for non-commercial projects.
113
+
114
+ Please use `Qwen2-7b-Instruct bf16` and `AutoCoder.IQ4_K.gguf` as alternatives for commericial activities.
115
+
116
+ <br>
117
+
118
  ## Download
119
 
120
  ```