Update README.md
Browse files
README.md
CHANGED
|
@@ -3,4 +3,18 @@ pipeline_tag: text-generation
|
|
| 3 |
tags:
|
| 4 |
- llama
|
| 5 |
- ggml
|
| 6 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- llama
|
| 5 |
- ggml
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
**Quantization from:**
|
| 9 |
+
[bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-fp16](https://huggingface.co/bhenrym14/airoboros-33b-gpt4-1.4.1-PI-8192-fp16)
|
| 10 |
+
|
| 11 |
+
**Converted to the GGML format with:**
|
| 12 |
+
[llama.cpp master-6e7cca4 (JUL 15, 2023)](https://github.com/ggerganov/llama.cpp/releases/tag/master-6e7cca4)
|
| 13 |
+
|
| 14 |
+
**Tested with:**
|
| 15 |
+
[koboldcpp 1.35](https://github.com/LostRuins/koboldcpp/releases/tag/v1.35)
|
| 16 |
+
|
| 17 |
+
**Example usage:**
|
| 18 |
+
```
|
| 19 |
+
koboldcpp.exe airoboros-33b-gpt4-1.4.1-PI-8192-fp16-GGML-Q2_K.bin --threads 6 --linearrope --contextsize 8192 --stream --smartcontext --unbantokens --noblas
|
| 20 |
+
```
|