Update README.md
Browse files
README.md
CHANGED
|
@@ -24,5 +24,42 @@ ggc c2
|
|
| 24 |
|
| 25 |
### **review/reference**
|
| 26 |
- simply execute the command (`ggc c2`) above in console/terminal
|
| 27 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
- gguf-connector ([pypi](https://pypi.org/project/gguf-connector))
|
|
|
|
| 24 |
|
| 25 |
### **review/reference**
|
| 26 |
- simply execute the command (`ggc c2`) above in console/terminal
|
| 27 |
+
- opt a `vae`, opt a `clip(encoder)` then opt a `model` file in the current directory to interact (see example below)
|
| 28 |
+
|
| 29 |
+
>
|
| 30 |
+
>GGUF file(s) available. Select which one for ve:
|
| 31 |
+
>
|
| 32 |
+
>1. t3_cfg-q2_k.gguf
|
| 33 |
+
>2. t3_cfg-q4_k_m.gguf
|
| 34 |
+
>3. t3_cfg-q6_k.gguf
|
| 35 |
+
>4. ve_fp32-f16.gguf
|
| 36 |
+
>5. ve_fp32-f32.gguf
|
| 37 |
+
>
|
| 38 |
+
>Enter your choice (1 to 5): 4
|
| 39 |
+
>
|
| 40 |
+
>ve file: ve_fp32-f16.gguf is selected!
|
| 41 |
+
>
|
| 42 |
+
>GGUF file(s) available. Select which one for t3:
|
| 43 |
+
>
|
| 44 |
+
>1. t3_cfg-q2_k.gguf
|
| 45 |
+
>2. t3_cfg-q4_k_m.gguf
|
| 46 |
+
>3. t3_cfg-q6_k.gguf
|
| 47 |
+
>4. ve_fp32-f16.gguf
|
| 48 |
+
>5. ve_fp32-f32.gguf
|
| 49 |
+
>
|
| 50 |
+
>Enter your choice (1 to 5): 2
|
| 51 |
+
>
|
| 52 |
+
>t3 file: t3_cfg-q4_k_m.gguf is selected!
|
| 53 |
+
>
|
| 54 |
+
>Safetensors file(s) available. Select which one for s3gen:
|
| 55 |
+
>
|
| 56 |
+
>1. s3gen_bf16.safetensors (recommended)
|
| 57 |
+
>2. s3gen_fp16.safetensors (for non-cuda user)
|
| 58 |
+
>3. s3gen_fp32.safetensors
|
| 59 |
+
>
|
| 60 |
+
>Enter your choice (1 to 3): _
|
| 61 |
+
>
|
| 62 |
+
|
| 63 |
+
- note: for the latest update, only tokenizer will be pulled to cache automatically during the first launch; you need to prepare the model, encoder and vae files yourself, working like [vision](https://huggingface.co/calcuis/llava-gguf) connector right away; mix and match, more flexible
|
| 64 |
+
- run it entirely offline; i.e., from local URL: http://127.0.0.1:7860 with lazy webui
|
| 65 |
- gguf-connector ([pypi](https://pypi.org/project/gguf-connector))
|