Xin Liu
commited on
Commit
·
68717c9
1
Parent(s):
6130bf2
rename projector file
Browse filesSigned-off-by: Xin Liu <sam@secondstate.io>
README.md
CHANGED
@@ -39,7 +39,7 @@ quantized_by: Second State Inc.
|
|
39 |
- Run as LlamaEdge service
|
40 |
|
41 |
```bash
|
42 |
-
wasmedge --dir .:. --nn-preload default:GGML:AUTO:llava-v1.5-7b-Q5_K_M.gguf llama-api-server.wasm -p vicuna-llava -c 2048 --llava-mmproj mmproj-model-f16.gguf -m llava-v1.5
|
43 |
```
|
44 |
|
45 |
## Quantized GGUF Models
|
@@ -58,6 +58,6 @@ quantized_by: Second State Inc.
|
|
58 |
| [llava-v1.5-7b-Q5_K_S.gguf](https://huggingface.co/second-state/Llava-v1.5-7B-GGUF/blob/main/llava-v1.5-7b-Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| large, low quality loss - recommended |
|
59 |
| [llava-v1.5-7b-Q6_K.gguf](https://huggingface.co/second-state/Llava-v1.5-7B-GGUF/blob/main/llava-v1.5-7b-Q6_K.gguf) | Q6_K | 6 | 5.53 GB| very large, extremely low quality loss |
|
60 |
| [llava-v1.5-7b-Q8_0.gguf](https://huggingface.co/second-state/Llava-v1.5-7B-GGUF/blob/main/llava-v1.5-7b-Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| very large, extremely low quality loss - not recommended |
|
61 |
-
| [mmproj-model-f16.gguf](https://huggingface.co/second-state/Llava-v1.5-7B-GGUF/blob/main/mmproj-model-f16.gguf) | f16 | 8 | 624 MB| |
|
62 |
|
63 |
*Quantized with llama.cpp b2230*
|
|
|
39 |
- Run as LlamaEdge service
|
40 |
|
41 |
```bash
|
42 |
+
wasmedge --dir .:. --nn-preload default:GGML:AUTO:llava-v1.5-7b-Q5_K_M.gguf llama-api-server.wasm -p vicuna-llava -c 2048 --llava-mmproj llava-v1.5-7b-mmproj-model-f16.gguf -m llava-v1.5
|
43 |
```
|
44 |
|
45 |
## Quantized GGUF Models
|
|
|
58 |
| [llava-v1.5-7b-Q5_K_S.gguf](https://huggingface.co/second-state/Llava-v1.5-7B-GGUF/blob/main/llava-v1.5-7b-Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| large, low quality loss - recommended |
|
59 |
| [llava-v1.5-7b-Q6_K.gguf](https://huggingface.co/second-state/Llava-v1.5-7B-GGUF/blob/main/llava-v1.5-7b-Q6_K.gguf) | Q6_K | 6 | 5.53 GB| very large, extremely low quality loss |
|
60 |
| [llava-v1.5-7b-Q8_0.gguf](https://huggingface.co/second-state/Llava-v1.5-7B-GGUF/blob/main/llava-v1.5-7b-Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| very large, extremely low quality loss - not recommended |
|
61 |
+
| [llava-v1.5-7b-mmproj-model-f16.gguf](https://huggingface.co/second-state/Llava-v1.5-7B-GGUF/blob/main/llava-v1.5-7b-mmproj-model-f16.gguf) | f16 | 8 | 624 MB| |
|
62 |
|
63 |
*Quantized with llama.cpp b2230*
|
mmproj-model-f16.gguf → llava-v1.5-7b-mmproj-model-f16.gguf
RENAMED
File without changes
|