Update README.md
Browse files
README.md
CHANGED
@@ -14,22 +14,23 @@ CodeLlama-13B-QML is a large language model customized by the Qt Company for Fil
|
|
14 |
This model reaches a score of 79% on the QML100 Fill-In-The-Middle code completion benchmark for Qt6-compliant code. In comparison, GPT4o scored 62%, Claude 3.5 Sonnet scored 68%, and the base CodeLlama-13B-hf 66%. This model was fine-tuned based on raw data from over 4000 human-created QML code snippets using the LoRa fine-tuning method. CodeLlama-13B-QML is not optimised for the creation of Qt5-release compliant, C++, or Python code.
|
15 |
|
16 |
## Terms of use:
|
17 |
-
By accessing this model, you are agreeing to the Llama 2 terms and conditions of the [license](https://github.com/meta-llama/llama/blob/main/LICENSE), [acceptable use policy](https://github.com/meta-llama/llama/blob/main/USE_POLICY.md) and [Meta’s privacy policy](https://www.facebook.com/privacy/policy/). By using this model, you are furthermore agreeing to [Qt AI Model terms & conditions](https://www.qt.io/terms-conditions).
|
18 |
|
19 |
## Usage:
|
20 |
Large language models, including CodeLlama-13B-QML, are not designed to be deployed in isolation but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building AI systems.
|
21 |
|
22 |
## How to run CodeLlama 13B-QML in ollama:
|
|
|
|
|
|
|
23 |
#### 1. Install ollama
|
24 |
https://ollama.com/download
|
25 |
|
26 |
-
|
27 |
-
|
28 |
-
#### 2. Download model repository
|
29 |
|
30 |
#### 3. Open the terminal and go to the repository
|
31 |
|
32 |
-
#### 4. Build model in ollama
|
33 |
```
|
34 |
ollama create <your-model-name> -f Modelfile
|
35 |
e.g. ollama create customcodellama13bqml -f Modelfile
|
@@ -67,6 +68,5 @@ If there is no suffix, please use:
|
|
67 |
```
|
68 |
|
69 |
|
70 |
-
|
71 |
## Model Version:
|
72 |
v1.0
|
|
|
14 |
This model reaches a score of 79% on the QML100 Fill-In-The-Middle code completion benchmark for Qt6-compliant code. In comparison, GPT4o scored 62%, Claude 3.5 Sonnet scored 68%, and the base CodeLlama-13B-hf 66%. This model was fine-tuned based on raw data from over 4000 human-created QML code snippets using the LoRa fine-tuning method. CodeLlama-13B-QML is not optimised for the creation of Qt5-release compliant, C++, or Python code.
|
15 |
|
16 |
## Terms of use:
|
17 |
+
By accessing this model, you are agreeing to the Llama 2 terms and conditions of the [license](https://github.com/meta-llama/llama/blob/main/LICENSE), [acceptable use policy](https://github.com/meta-llama/llama/blob/main/USE_POLICY.md) and [Meta’s privacy policy](https://www.facebook.com/privacy/policy/). By using this model, you are furthermore agreeing to the [Qt AI Model terms & conditions](https://www.qt.io/terms-conditions).
|
18 |
|
19 |
## Usage:
|
20 |
Large language models, including CodeLlama-13B-QML, are not designed to be deployed in isolation but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building AI systems.
|
21 |
|
22 |
## How to run CodeLlama 13B-QML in ollama:
|
23 |
+
|
24 |
+
Note: These instructions are written for ollama version 0.5.7.
|
25 |
+
|
26 |
#### 1. Install ollama
|
27 |
https://ollama.com/download
|
28 |
|
29 |
+
#### 2. Download the model repository
|
|
|
|
|
30 |
|
31 |
#### 3. Open the terminal and go to the repository
|
32 |
|
33 |
+
#### 4. Build the model in ollama
|
34 |
```
|
35 |
ollama create <your-model-name> -f Modelfile
|
36 |
e.g. ollama create customcodellama13bqml -f Modelfile
|
|
|
68 |
```
|
69 |
|
70 |
|
|
|
71 |
## Model Version:
|
72 |
v1.0
|