Commit
•
55af565
1
Parent(s):
2515821
Rename README-2.md to README.md
Browse files- README-2.md → README.md +13 -8
README-2.md → README.md
RENAMED
|
@@ -1,15 +1,20 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
-
pipeline_tag: text-generation
|
| 5 |
-
tags:
|
| 6 |
-
- facebook
|
| 7 |
-
- meta
|
| 8 |
-
- pytorch
|
| 9 |
-
- llama
|
| 10 |
-
- llama-3
|
| 11 |
-
- axolotl
|
| 12 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
## Llama 3 8B 256K
|
| 15 |
|
|
|
|
| 1 |
---
|
| 2 |
+
---
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
language:
|
| 5 |
- en
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
+
quantized_by: KnightCodin
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
## Exllama v2 Quantizations of winglian/Llama-3-8b-256k-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 |
|
| 19 |
## Llama 3 8B 256K
|
| 20 |
|