AI/Microsoft-fara
1
0
Fork 0
mirror of https://github.com/microsoft/fara.git synced 2026-06-10 02:54:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

readme update

Browse Source
This commit is contained in:
Alexey Taymanov
2025-11-25 03:33:00 +00:00
parent 9edb064d9c
commit b37cd4eb33
1 changed files with 3 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@@ -173,6 +173,8 @@ The script will download the model to `model_checkpoints/fara-7b/` by default. Y
Second, host the model locally on a GPU machine:
```bash
cd src/fara/vllm
python -m pip install -r requirements.txt
python az_vllm.py --model_url /path/to/model_checkpoints/ --device_id 0,1
```
@@ -186,7 +188,7 @@ Run the test script to see Fara in action:
python test_fara_agent.py --task "how many pages does wikipedia have" --start_page "https://www.bing.com" --endpoint_config endpoint_configs/azure_foundry_config.json [--headful] [--downloads_folder "/path/to/downloads"] [--save_screenshots] [--max_rounds 100] [--browserbase]
```
The `client_config` points to `"base_url": "http://localhost:5000/v1"` from the VLLM server above.
In self-hosting scenario the `endpoint_config` points to `endpoint_configs/vllm_config.json` from the VLLM server above.
If you set `--browserbase`, export environment variables for the API key and project ID.