kevinlu1248 commited on
Commit
abc1022
·
verified ·
1 Parent(s): 5193e38

Use HTML table to remove header line

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -86,14 +86,14 @@ updated:
86
 
87
  Fine-tuned from [Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) on developer editing traces using SFT, then GRPO, then DPO.
88
 
89
- | | |
90
- |---|---|
91
- | Base model | Qwen2.5-Coder-7B |
92
- | Fine-tuning | SFT → GRPO → DPO |
93
- | Parameters | 7B |
94
- | Precision | bfloat16 |
95
- | Context length | 32,768 tokens |
96
- | Architecture | Qwen2 (28 layers, hidden dim 3584) |
97
- | Stop tokens | `<\|endoftext\|>`, `<\|file_sep\|>` |
98
- | Max output tokens | 1024 |
99
- | Decoding | Greedy (temperature=0) |
 
86
 
87
  Fine-tuned from [Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B) on developer editing traces using SFT, then GRPO, then DPO.
88
 
89
+ <table>
90
+ <tr><td>Base model</td><td>Qwen2.5-Coder-7B</td></tr>
91
+ <tr><td>Fine-tuning</td><td>SFT GRPO DPO</td></tr>
92
+ <tr><td>Parameters</td><td>7B</td></tr>
93
+ <tr><td>Precision</td><td>bfloat16</td></tr>
94
+ <tr><td>Context length</td><td>32,768 tokens</td></tr>
95
+ <tr><td>Architecture</td><td>Qwen2 (28 layers, hidden dim 3584)</td></tr>
96
+ <tr><td>Stop tokens</td><td><code>&lt;|endoftext|&gt;</code>, <code>&lt;|file_sep|&gt;</code></td></tr>
97
+ <tr><td>Max output tokens</td><td>1024</td></tr>
98
+ <tr><td>Decoding</td><td>Greedy (temperature=0)</td></tr>
99
+ </table>