Update README.md
Browse files
README.md
CHANGED
|
@@ -15,29 +15,38 @@ tags:
|
|
| 15 |
- programming
|
| 16 |
---
|
| 17 |
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model Details:
|
| 21 |
-
- **Model Name:**
|
| 22 |
- **Base Model:** gemini-2.0-flash-lite-001
|
| 23 |
- **Tuning Method:** Supervised
|
| 24 |
|
| 25 |
## Tuning Information:
|
| 26 |
-
- **Tuning Job:** projects/903806786624/locations/us-central1/tuningJobs/6829066050101837824
|
| 27 |
-
- **Tuning Dataset:** gs://fine-tuning-main/vertex_system.jsonl
|
| 28 |
-
- **Experiment:** tuning-experiment-20250610065357274903
|
| 29 |
- **Number of Epochs:** 25
|
| 30 |
-
- **Intermediate Checkpoints:** Enabled
|
| 31 |
- **Default Checkpoint:** 8
|
| 32 |
- **Learning Rate Multiplier:** 0.004
|
| 33 |
- **Adapter Size:** 4
|
| 34 |
-
- **Truncated Example Count:** 0
|
| 35 |
|
| 36 |
## Performance and Status:
|
| 37 |
- **Status:** Succeeded
|
| 38 |
- **Region:** us-central1
|
| 39 |
- **Created:** June 10, 2025, 7:52:44 AM
|
| 40 |
-
- **Ended:** June 10, 2025, 8:09:47
|
| 41 |
-
|
| 42 |
-
## Security and Compliance:
|
| 43 |
-
- **Encryption Type:** Google-managed
|
|
|
|
| 15 |
- programming
|
| 16 |
---
|
| 17 |
|
| 18 |
+
1. Model Details:
|
| 19 |
+
Model Name: framer_overrides (as you prov
|
| 20 |
+
Model Type:Fine-tuned Gemini 1.5 Pr on Framer Custom Code Overrides and Code Components
|
| 21 |
+
Original Model: Gemini 2.5 pro
|
| 22 |
+
Fine-tuning Method: Supervised fine-tuning.
|
| 23 |
+
2. Deployment Information:
|
| 24 |
+
Deployment Platform: Google Cloud Vertex AI.
|
| 25 |
+
Endpoint ID: 7750638883611607040 (This is important for identifying the specific deployment).
|
| 26 |
+
Region: us-central1 .
|
| 27 |
+
API Endpoint: fra
|
| 28 |
+
Infrastructure: Google-managed.
|
| 29 |
+
Model Status: Active
|
| 30 |
+
## How to use:
|
| 31 |
+
**Install the Vertex AI SDK: Open a terminal window and enter the command below. You can also install it in a virtualenv**
|
| 32 |
+
```pip install --upgrade google-genaigcloud auth application-default login```
|
| 33 |
+
|
| 34 |
+
**Use the following code in your application to request a model response**
|
| 35 |
+
```from google import genaifrom google.genai import typesimport base64def generate(): client = genai.Client( vertexai=True, project="903806786624", location="us-central1", ) model = "projects/903806786624/locations/us-central1/endpoints/2455637174847012864" contents = [ types.Content( role="user", parts=[ ] ) ] generate_content_config = types.GenerateContentConfig( temperature = 1, top_p = 0.95, max_output_tokens = 8192, safety_settings = [types.SafetySetting( category="HARM_CATEGORY_HATE_SPEECH", threshold="OFF" ),types.SafetySetting( category="HARM_CATEGORY_DANGEROUS_CONTENT", threshold="OFF" ),types.SafetySetting( category="HARM_CATEGORY_SEXUALLY_EXPLICIT", threshold="OFF" ),types.SafetySetting( category="HARM_CATEGORY_HARASSMENT", threshold="OFF" )], )```
|
| 36 |
|
| 37 |
## Model Details:
|
| 38 |
+
- **Model Name:** framer_custom_code
|
| 39 |
- **Base Model:** gemini-2.0-flash-lite-001
|
| 40 |
- **Tuning Method:** Supervised
|
| 41 |
|
| 42 |
## Tuning Information:
|
|
|
|
|
|
|
|
|
|
| 43 |
- **Number of Epochs:** 25
|
|
|
|
| 44 |
- **Default Checkpoint:** 8
|
| 45 |
- **Learning Rate Multiplier:** 0.004
|
| 46 |
- **Adapter Size:** 4
|
|
|
|
| 47 |
|
| 48 |
## Performance and Status:
|
| 49 |
- **Status:** Succeeded
|
| 50 |
- **Region:** us-central1
|
| 51 |
- **Created:** June 10, 2025, 7:52:44 AM
|
| 52 |
+
- **Ended:** June 10, 2025, 8:09:47
|
|
|
|
|
|
|
|
|