ti.sil/pr-agent
1
0
Fork 0
mirror of https://github.com/qodo-ai/pr-agent.git synced 2025-12-13 11:25:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Optimize for fine-tuning impact table

Browse source
This commit is contained in:
KennyDizi 2024-06-01 08:11:34 +07:00
parent b9aeb8e443
commit 85f6353d15
1 changed files with 5 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
docs/docs/finetuning_benchmark/index.md
View file

@ -33,29 +33,12 @@ Here are the results:
<br>
**Fine-tuning impact:**
<body>
<table>
<tr>
<th align="center">Model name</th>
<th>Model size [B]</th>
<th>Fine-tuned</th>
<th>Better than gpt-4 rate [%]</th>
</tr>
<tr>
<td align="center">DeepSeek 34B-instruct</td>
<td align="center">34</td>
<td align="center">yes</td>
<td align="center">40.7</td>
</tr>
<tr>
<td align="center">DeepSeek 34B-instruct</td>
<td align="center">34</td>
<td align="center">no</td>
<td align="center">3.6</td>
</tr>
</table>
**Fine-tuning impact:**
</body>
| Model name | Model size [B] | Fine-tuned | Better than gpt-4 rate [%] |
|---------------------------|----------------|------------|----------------------------|
| DeepSeek 34B-instruct | 34 | yes | 40.7 |
| DeepSeek 34B-instruct | 34 | no | 3.6 |
## Results analysis