Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,13 @@ quantized_by: KnightCodin
|
|
| 8 |
---
|
| 9 |
|
| 10 |
## Exllama v2 Quantizations of winglian/Llama-3-8b-64k-PoSE
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
pipeline_tag: text-generation
|
| 12 |
tags:
|
| 13 |
- facebook
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
## Exllama v2 Quantizations of winglian/Llama-3-8b-64k-PoSE
|
| 11 |
+
|
| 12 |
+
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.19">turboderp's ExLlamaV2 v0.0.19</a> for quantization.
|
| 13 |
+
|
| 14 |
+
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
|
| 15 |
+
|
| 16 |
+
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
|
| 17 |
+
|
| 18 |
pipeline_tag: text-generation
|
| 19 |
tags:
|
| 20 |
- facebook
|