docs: add Tested inference path section, reorganize model card
Browse files
README.md
CHANGED
|
@@ -53,6 +53,20 @@ datasets:
|
|
| 53 |
|
| 54 |
This card only reports metadata present in the Hugging Face repository, existing card frontmatter, or public config files. Missing benchmark, dataset, or training-run details are left explicit rather than reconstructed.
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
## Usage
|
| 57 |
|
| 58 |
### Python
|
|
@@ -72,7 +86,7 @@ document_image = "page.png"
|
|
| 72 |
|
| 73 |
## Example output
|
| 74 |
|
| 75 |
-
No public sample output is currently declared for this checkpoint.
|
| 76 |
|
| 77 |
## Comparison with the base model
|
| 78 |
|
|
@@ -104,15 +118,6 @@ No public sample output is currently declared for this checkpoint. Run the usage
|
|
| 104 |
note = {MLX checkpoint published by LibraxisAI}
|
| 105 |
}
|
| 106 |
```
|
| 107 |
-
|
| 108 |
-
## Inference tested on
|
| 109 |
-
|
| 110 |
-
[`LibraxisAI/mlx-batch-server`](https://github.com/LibraxisAI/mlx-batch-server)
|
| 111 |
-
|
| 112 |
-
## Related
|
| 113 |
-
|
| 114 |
-
- Base model: [`tomoro-ai/Colqwen3-8B-base`](https://huggingface.co/tomoro-ai/Colqwen3-8B-base)
|
| 115 |
-
|
| 116 |
---
|
| 117 |
|
| 118 |
π
ππππππππππ. with AI Agents by VetCoders (c)2024-2026 LibraxisAI
|
|
|
|
| 53 |
|
| 54 |
This card only reports metadata present in the Hugging Face repository, existing card frontmatter, or public config files. Missing benchmark, dataset, or training-run details are left explicit rather than reconstructed.
|
| 55 |
|
| 56 |
+
## Tested inference path
|
| 57 |
+
|
| 58 |
+
> **Inference for this checkpoint has been tested with [`LibraxisAI/mlx-batch-server`](https://github.com/LibraxisAI/mlx-batch-server).**\
|
| 59 |
+
> This is the recommended tested path for operator-controlled local inference on Apple Silicon.
|
| 60 |
+
|
| 61 |
+
| Aspect | Status |
|
| 62 |
+
|---|---|
|
| 63 |
+
| Tested runtime | `LibraxisAI/mlx-batch-server` |
|
| 64 |
+
| Target hardware | Apple Silicon |
|
| 65 |
+
| Inference mode | Local / self-hosted |
|
| 66 |
+
| Hugging Face Hosted Inference | Disabled for this repository (`inference: false`) |
|
| 67 |
+
|
| 68 |
+
This does not claim compatibility with every possible serving stack. It documents the path that has been exercised for this published checkpoint.
|
| 69 |
+
|
| 70 |
## Usage
|
| 71 |
|
| 72 |
### Python
|
|
|
|
| 86 |
|
| 87 |
## Example output
|
| 88 |
|
| 89 |
+
No public sample output is currently declared for this checkpoint.
|
| 90 |
|
| 91 |
## Comparison with the base model
|
| 92 |
|
|
|
|
| 118 |
note = {MLX checkpoint published by LibraxisAI}
|
| 119 |
}
|
| 120 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
---
|
| 122 |
|
| 123 |
π
ππππππππππ. with AI Agents by VetCoders (c)2024-2026 LibraxisAI
|