| --- |
| base_model: microsoft/Fara-7B |
| license: mit |
| pipeline_tag: image-text-to-text |
| tags: |
| - qwen2_5_vl |
| - computer-use |
| - web-agent |
| --- |
| |
| # cua-lite/Fara-7B |
|
|
| A **config-only fix** of [`microsoft/Fara-7B`](https://huggingface.co/microsoft/Fara-7B). |
| The model weights are **identical** to the upstream release — only `config.json` |
| is changed to make the model load under **transformers v5 + SGLang**. |
|
|
| ## What changed |
|
|
| `microsoft/Fara-7B` ships a transformers-4.x `config.json` where `rope_theta` |
| and `rope_scaling` are separate top-level fields. Under transformers v5 (the |
| "untangle config" refactor), SGLang reads RoPE parameters via the computed |
| `config.rope_parameters` property and passes the **top-level** `Qwen2_5_VLConfig` |
| (not `text_config`) into `Qwen2Model`. For that top-level config, |
| `rope_parameters` returns `rope_scaling` **without** folding in `rope_theta`, so |
| SGLang's `get_rope_config` hits `rope_params["rope_theta"]` and dies at load: |
|
|
| ``` |
| KeyError: 'rope_theta' |
| ``` |
|
|
| This fork folds `rope_theta` **into** `rope_scaling` (at both the top level and |
| in `text_config`) so `rope_parameters` exposes it: |
|
|
| ```json |
| "rope_scaling": { |
| "mrope_section": [16, 24, 24], |
| "rope_type": "default", |
| "type": "default", |
| "rope_theta": 1000000.0 |
| } |
| ``` |
|
|
| `rope_theta` is also kept as a top-level key for transformers-4.x backward |
| compatibility. Nothing else is modified — tokenizer, preprocessor, chat |
| template, and all safetensors shards are byte-identical to upstream. |
|
|
| ## Usage (SGLang) |
|
|
| ```bash |
| python -m sglang.launch_server \ |
| --model-path cua-lite/Fara-7B \ |
| --host 0.0.0.0 --port 30088 |
| ``` |
|
|
| Or, keeping `microsoft/Fara-7B` as the logical model id and only overriding the |
| weights/config path: |
|
|
| ```bash |
| python scripts/serve_sglang.py \ |
| --model-id microsoft/Fara-7B \ |
| --model-path cua-lite/Fara-7B \ |
| --port 30088 |
| ``` |
|
|
| ## License & attribution |
|
|
| All rights, license, and model behavior follow the upstream model. See |
| [`microsoft/Fara-7B`](https://huggingface.co/microsoft/Fara-7B) for the model |
| card, intended use, and limitations. |
|
|
