Update README.md
Browse files
README.md
CHANGED
|
@@ -28,7 +28,7 @@ The abliterated model will no longer say "I'm sorry, but I can't assist with tha
|
|
| 28 |
|
| 29 |
## Chat with Image
|
| 30 |
|
| 31 |
-
### [llama.cpp](https://github.com/ggml-org/llama.cpp) Inference
|
| 32 |
|
| 33 |
(llama-mtmd-cli needs to be compiled.)
|
| 34 |
|
|
@@ -36,7 +36,7 @@ The abliterated model will no longer say "I'm sorry, but I can't assist with tha
|
|
| 36 |
llama-mtmd-cli -m huihui-ai/Huihui-Qwen3-8B-abliterated/GGUF/ggml-model-Q4_K_M.gguf --mmproj huihui-ai/Huihui-Qwen3-8B-abliterated/GGUF/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image abc.png -p "What is in the image?"
|
| 37 |
```
|
| 38 |
|
| 39 |
-
###
|
| 40 |
|
| 41 |
|
| 42 |
```
|
|
|
|
| 28 |
|
| 29 |
## Chat with Image
|
| 30 |
|
| 31 |
+
### 1. [llama.cpp](https://github.com/ggml-org/llama.cpp) Inference
|
| 32 |
|
| 33 |
(llama-mtmd-cli needs to be compiled.)
|
| 34 |
|
|
|
|
| 36 |
llama-mtmd-cli -m huihui-ai/Huihui-Qwen3-8B-abliterated/GGUF/ggml-model-Q4_K_M.gguf --mmproj huihui-ai/Huihui-Qwen3-8B-abliterated/GGUF/mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1.05 --image abc.png -p "What is in the image?"
|
| 37 |
```
|
| 38 |
|
| 39 |
+
### 2. Transfromers Inference
|
| 40 |
|
| 41 |
|
| 42 |
```
|