Welcome to Software Development on Codidact!
Will you help us build our independent community of developers helping developers? We're small and trying to grow. We welcome questions about all aspects of software development, from design to code to QA and more. Got questions? Got answers? Got code you'd like someone to review? Please join us.
Post History
I follow Azure's tutorial on fine-tuning GPT. I follow the deployment phase. Code: # Deploy fine-tuned model import json import requests token = '[redacted]' subscription = '[redacted]' ...
#3: Post edited
by
Lundin
·
2025-04-15T13:56:12Z (4 days ago)
Not a tag related to programming.
#2: Post edited
by
Franck Dernoncourt
·
2025-04-14T19:36:09Z (4 days ago)
I follow Azure's [tutorial](https://learn.microsoft.com/en-us/azure/ai-services/openai/tutorials/fine-tune?tabs=python-new%2Ccommand-line) on fine-tuning GPT. I'm stuck at the deployment phase.- Code:
- ```
- # Deploy fine-tuned model
- import json
- import requests
- token = '[redacted]'
- subscription = '[redacted]'
- resource_group = "[redacted]"
- resource_name = "[redacted]"
- model_deployment_name = "gpt-4o-mini-2024-07-18-ft" # Custom deployment name you chose for your fine-tuning model
- deploy_params = {'api-version': "2023-05-01"}
- deploy_headers = {'Authorization': 'Bearer {}'.format(token), 'Content-Type': 'application/json'}
- deploy_data = {
- "sku": {"name": "standard", "capacity": 1},
- "properties": {
- "model": {
- "format": "OpenAI",
- "name": "gpt-4o-mini-2024-07-18.ft-[redacted]", #retrieve this value from the previous call, it will look like gpt-4o-mini-2024-07-18.ft-[redacted]
- "version": "1"
- }
- }
- }
- deploy_data = json.dumps(deploy_data)
- request_url = f'https://management.azure.com/subscriptions/{subscription}/resourceGroups/{resource_group}/providers/Microsoft.CognitiveServices/accounts/{resource_name}/deployments/{model_deployment_name}'
- print('Creating a new deployment...')
- r = requests.put(request_url, params=deploy_params, headers=deploy_headers, data=deploy_data)
- print(r)
- print(r.reason)
- print(r.json())
- ```
- That works fine, but the token expires quickly. This annoys me. How can I deploy a fine-tuned GPT model in Azure via Python without using a token (e.g., using an endpoint key instead)?
- -----
- Crossposts
- - https://qr.ae/pAstMk
- - https://redd.it/1jz7qmu
- - https://redd.it/1jz7qqv
- - https://redd.it/1jz7qvi
- - https://stackoverflow.com/q/79573882/395857
- I follow Azure's [tutorial](https://learn.microsoft.com/en-us/azure/ai-services/openai/tutorials/fine-tune?tabs=python-new%2Ccommand-line) on fine-tuning GPT. I follow the deployment phase.
- Code:
- ```
- # Deploy fine-tuned model
- import json
- import requests
- token = '[redacted]'
- subscription = '[redacted]'
- resource_group = "[redacted]"
- resource_name = "[redacted]"
- model_deployment_name = "gpt-4o-mini-2024-07-18-ft" # Custom deployment name you chose for your fine-tuning model
- deploy_params = {'api-version': "2023-05-01"}
- deploy_headers = {'Authorization': 'Bearer {}'.format(token), 'Content-Type': 'application/json'}
- deploy_data = {
- "sku": {"name": "standard", "capacity": 1},
- "properties": {
- "model": {
- "format": "OpenAI",
- "name": "gpt-4o-mini-2024-07-18.ft-[redacted]", #retrieve this value from the previous call, it will look like gpt-4o-mini-2024-07-18.ft-[redacted]
- "version": "1"
- }
- }
- }
- deploy_data = json.dumps(deploy_data)
- request_url = f'https://management.azure.com/subscriptions/{subscription}/resourceGroups/{resource_group}/providers/Microsoft.CognitiveServices/accounts/{resource_name}/deployments/{model_deployment_name}'
- print('Creating a new deployment...')
- r = requests.put(request_url, params=deploy_params, headers=deploy_headers, data=deploy_data)
- print(r)
- print(r.reason)
- print(r.json())
- ```
- That works fine, but the token expires quickly. This annoys me. How can I deploy a fine-tuned GPT model in Azure via Python without using a token (e.g., using an endpoint key instead)?
- -----
- Crossposts
- - https://qr.ae/pAstMk
- - https://redd.it/1jz7qmu
- - https://redd.it/1jz7qqv
- - https://redd.it/1jz7qvi
- - https://stackoverflow.com/q/79573882/395857
#1: Initial revision
by
Franck Dernoncourt
·
2025-04-14T19:34:13Z (4 days ago)
How can I deploy a fine-tuned GPT model in Azure via Python without using a token (e.g., using an endpoint key instead)?
I follow Azure's [tutorial](https://learn.microsoft.com/en-us/azure/ai-services/openai/tutorials/fine-tune?tabs=python-new%2Ccommand-line) on fine-tuning GPT. I'm stuck at the deployment phase.
Code:
```
# Deploy fine-tuned model
import json
import requests
token = '[redacted]'
subscription = '[redacted]'
resource_group = "[redacted]"
resource_name = "[redacted]"
model_deployment_name = "gpt-4o-mini-2024-07-18-ft" # Custom deployment name you chose for your fine-tuning model
deploy_params = {'api-version': "2023-05-01"}
deploy_headers = {'Authorization': 'Bearer {}'.format(token), 'Content-Type': 'application/json'}
deploy_data = {
"sku": {"name": "standard", "capacity": 1},
"properties": {
"model": {
"format": "OpenAI",
"name": "gpt-4o-mini-2024-07-18.ft-[redacted]", #retrieve this value from the previous call, it will look like gpt-4o-mini-2024-07-18.ft-[redacted]
"version": "1"
}
}
}
deploy_data = json.dumps(deploy_data)
request_url = f'https://management.azure.com/subscriptions/{subscription}/resourceGroups/{resource_group}/providers/Microsoft.CognitiveServices/accounts/{resource_name}/deployments/{model_deployment_name}'
print('Creating a new deployment...')
r = requests.put(request_url, params=deploy_params, headers=deploy_headers, data=deploy_data)
print(r)
print(r.reason)
print(r.json())
```
That works fine, but the token expires quickly. This annoys me. How can I deploy a fine-tuned GPT model in Azure via Python without using a token (e.g., using an endpoint key instead)?
-----
Crossposts
- https://qr.ae/pAstMk
- https://redd.it/1jz7qmu
- https://redd.it/1jz7qqv
- https://redd.it/1jz7qvi
- https://stackoverflow.com/q/79573882/395857