Ubuntu
commited on
Commit
·
7dfb604
1
Parent(s):
8af2590
Add readme
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- llava
|
| 4 |
+
- bakllava
|
| 5 |
+
- lmm
|
| 6 |
+
- ggml
|
| 7 |
+
- llama.cpp
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# ggml_bakllava-1
|
| 11 |
+
|
| 12 |
+
This repo contains GGUF files to inference [BakLLaVA-1](https://huggingface.co/SkunkworksAI/BakLLaVA-1) with [llama.cpp](https://github.com/ggerganov/llama.cpp) end-to-end without any extra dependency.
|
| 13 |
+
|
| 14 |
+
**Note**: The `mmproj-model-f16.gguf` file structure is experimental and may change. Always use the latest code in llama.cpp.
|