Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ Alpaca 30B 4-bit working with GPTQ versions used in Oobabooga's Text Generation
|
|
4 |
This was made using Chansung's 30B Alpaca Lora: https://huggingface.co/chansung/alpaca-lora-30b
|
5 |
|
6 |
<p><strong><font size="5">Update 04.06.2023</font></strong></p>
|
7 |
-
<p>This is a more recent merge of Chansung's Alpaca Lora which was updated using the clean alpaca dataset as of 04/06/2023
|
8 |
<p><strong>Training Parameters</strong></p>
|
9 |
<ul><li>num_epochs=10</li><li>cutoff_len=512</li><li>group_by_length</li><li>lora_target_modules='[q_proj,k_proj,v_proj,o_proj]'</li><li>lora_r=16</li><li>micro_batch_size=8</li></ul>
|
10 |
<p><strong><font size="5">Benchmarks</font></strong></p>
|
|
|
4 |
This was made using Chansung's 30B Alpaca Lora: https://huggingface.co/chansung/alpaca-lora-30b
|
5 |
|
6 |
<p><strong><font size="5">Update 04.06.2023</font></strong></p>
|
7 |
+
<p>This is a more recent merge of Chansung's Alpaca Lora which was updated using the clean alpaca dataset as of 04/06/2023 with refined training parameters</p>
|
8 |
<p><strong>Training Parameters</strong></p>
|
9 |
<ul><li>num_epochs=10</li><li>cutoff_len=512</li><li>group_by_length</li><li>lora_target_modules='[q_proj,k_proj,v_proj,o_proj]'</li><li>lora_r=16</li><li>micro_batch_size=8</li></ul>
|
10 |
<p><strong><font size="5">Benchmarks</font></strong></p>
|