Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,8 @@ pipeline_tag: text-generation
|
|
| 5 |
tags:
|
| 6 |
- text-generation-inference
|
| 7 |
---
|
|
|
|
|
|
|
| 8 |
|
| 9 |

|
| 10 |
|
|
@@ -13,6 +15,7 @@ tags:
|
|
| 13 |
|
| 14 |
```
|
| 15 |
<|start_header_id|>system<|end_header_id|>
|
|
|
|
| 16 |
{system_prompt}<|eot_id|>
|
| 17 |
```
|
| 18 |
|
|
|
|
| 5 |
tags:
|
| 6 |
- text-generation-inference
|
| 7 |
---
|
| 8 |
+
> [!WARNING]
|
| 9 |
+
> At the time of this release, llama.cpp did not support the rope scaling required for full context (limit is 8192). Soon this will be updated for full 128K functionality.
|
| 10 |
|
| 11 |

|
| 12 |
|
|
|
|
| 15 |
|
| 16 |
```
|
| 17 |
<|start_header_id|>system<|end_header_id|>
|
| 18 |
+
|
| 19 |
{system_prompt}<|eot_id|>
|
| 20 |
```
|
| 21 |
|