Update README.md
#7
by
ZoeyShu
- opened
README.md
CHANGED
@@ -66,12 +66,22 @@ Example prompt to interact
|
|
66 |
```
|
67 |
|
68 |
## Run with [Ollama](https://github.com/ollama/ollama)
|
69 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
```bash
|
71 |
FROM ./path/to/octopus-v4-Q4_K_M.gguf
|
72 |
```
|
73 |
|
74 |
2. Use the following command to add the model to Ollama:
|
|
|
75 |
```bash
|
76 |
ollama create octopus-v4-Q4_K_M -f Modelfile
|
77 |
PARAMETER temperature 0
|
@@ -80,6 +90,7 @@ PARAMETER stop <nexa_end>
|
|
80 |
```
|
81 |
|
82 |
3. Verify that the model has been successfully imported:
|
|
|
83 |
```bash
|
84 |
ollama ls
|
85 |
```
|
|
|
66 |
```
|
67 |
|
68 |
## Run with [Ollama](https://github.com/ollama/ollama)
|
69 |
+
|
70 |
+
Since our models have not been uploaded to the Ollama server, please download the models and manually import them into <u>[Ollama]((https://github.com/ollama/ollama))</u> by following these steps:
|
71 |
+
|
72 |
+
1. Locate the local Ollama directory:
|
73 |
+
```bash
|
74 |
+
cd ollama
|
75 |
+
```
|
76 |
+
|
77 |
+
2. Create a `Modelfile` in your directory and include a `FROM` statement with the path to your local model:
|
78 |
+
|
79 |
```bash
|
80 |
FROM ./path/to/octopus-v4-Q4_K_M.gguf
|
81 |
```
|
82 |
|
83 |
2. Use the following command to add the model to Ollama:
|
84 |
+
|
85 |
```bash
|
86 |
ollama create octopus-v4-Q4_K_M -f Modelfile
|
87 |
PARAMETER temperature 0
|
|
|
90 |
```
|
91 |
|
92 |
3. Verify that the model has been successfully imported:
|
93 |
+
|
94 |
```bash
|
95 |
ollama ls
|
96 |
```
|