Text Generation
Transformers
English
llama
Not-For-All-Audiences
nsfw
text-generation-inference
Inference Endpoints
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,8 +15,11 @@ language:
|
|
| 15 |
First attempt to quantize a 20B model so it can run on 16GB VRAM with the highest quality possible.
|
| 16 |
Quantized at 3.23bpw with hb 6
|
| 17 |
Perplexity:
|
|
|
|
| 18 |
Base = 6.4744
|
|
|
|
| 19 |
3.23 h6 = 6.5369
|
|
|
|
| 20 |
Dataset = [wikitext](https://huggingface.co/datasets/wikitext/resolve/refs%2Fconvert%2Fparquet/wikitext-2-v1/test/0000.parquet)
|
| 21 |
|
| 22 |
## Prompt Format
|
|
|
|
| 15 |
First attempt to quantize a 20B model so it can run on 16GB VRAM with the highest quality possible.
|
| 16 |
Quantized at 3.23bpw with hb 6
|
| 17 |
Perplexity:
|
| 18 |
+
|
| 19 |
Base = 6.4744
|
| 20 |
+
|
| 21 |
3.23 h6 = 6.5369
|
| 22 |
+
|
| 23 |
Dataset = [wikitext](https://huggingface.co/datasets/wikitext/resolve/refs%2Fconvert%2Fparquet/wikitext-2-v1/test/0000.parquet)
|
| 24 |
|
| 25 |
## Prompt Format
|