Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,8 @@ pipeline_tag: text-generation
|
|
| 9 |
|
| 10 |
## Exllama v2 Quantizations of Llama-3-Hercules-5.1-8B
|
| 11 |
|
|
|
|
|
|
|
| 12 |
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.1.0">turboderp's ExLlamaV2 v0.1.0</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>
|
|
|
|
| 9 |
|
| 10 |
## Exllama v2 Quantizations of Llama-3-Hercules-5.1-8B
|
| 11 |
|
| 12 |
+
Llama-3-Hercules-5.0-8B was updated in place after another 0.5 epochs of training, labelling this 5.1 to avoid confusion
|
| 13 |
+
|
| 14 |
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.1.0">turboderp's ExLlamaV2 v0.1.0</a> for quantization.
|
| 15 |
|
| 16 |
<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
|