Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- OpenAssistant/oasst1
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
<p><strong><font size="5">Information</font></strong></p>
|
| 7 |
+
OpenAssistant-Alpaca-13B-4-bit working with GPTQ versions used in Oobabooga's Text Generation Webui and KoboldAI.
|
| 8 |
+
<br>This was made using https://huggingface.co/chavinlo/alpaca-13b and <a href="https://huggingface.co/serpdotai/llama-oasst-lora-13B">Serpdotai's Open Assistant 13b LoRa trained for 4 epochs</a> using Open Assistant's dataset.</p>
|
| 9 |
+
|
| 10 |
+
python llama.py /Models/alpaca13b-oaast4ep-lora c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors oasst-alpaca13b-4ep-lora-4bit-128g.safetensors
|
| 11 |
+
|
| 12 |
+
<p><strong><font size="5">Benchmarks</font></strong></p>
|
| 13 |
+
|
| 14 |
+
<p><strong><font size="4">--true-sequential --groupsize 128</font></strong></p>
|
| 15 |
+
|
| 16 |
+
<strong>Wikitext2</strong>: 6.854333400726318
|
| 17 |
+
|
| 18 |
+
<strong>Ptb-New</strong>: 12.411578178405762
|
| 19 |
+
|
| 20 |
+
<strong>C4-New</strong>: 9.355494499206543
|
| 21 |
+
|
| 22 |
+
<strong>Note</strong>: This version uses <i>--groupsize 128</i>, resulting in better evaluations.
|