Zero-Shot Classification
Transformers
Safetensors
English
qwen3_5
feature-extraction
jeff
decision-model
calibration
system-1
local
Instructions to use mstrasser/jeff-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mstrasser/jeff-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="mstrasser/jeff-base")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("mstrasser/jeff-base") model = AutoModel.from_pretrained("mstrasser/jeff-base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Card: adapter serving is on main of firelex/jeff; note on the recorded training commit
Browse files
README.md
CHANGED
|
@@ -134,8 +134,7 @@ starting with "jeff" mean the base model.
|
|
| 134 |
|
| 135 |
## How to use it
|
| 136 |
|
| 137 |
-
Adapter serving
|
| 138 |
-
[firelex/jeff](https://github.com/firelex/jeff).
|
| 139 |
|
| 140 |
```bash
|
| 141 |
git clone https://github.com/firelex/jeff && cd jeff
|
|
@@ -197,6 +196,7 @@ A data set written to the [data guidelines](https://jeffhub.ai/docs/data-guideli
|
|
| 197 |
| Built on | Qwen/Qwen3.5-0.8B |
|
| 198 |
| Data | The v1.2 base training data, unchanged |
|
| 199 |
| Change from v1.2 | The live-last prompt layout |
|
|
|
|
| 200 |
| Checkpoint | `ll-v12-final` (run `ll-v12`, step 1113) |
|
| 201 |
|
| 202 |
## Not measured yet
|
|
|
|
| 134 |
|
| 135 |
## How to use it
|
| 136 |
|
| 137 |
+
Adapter serving is part of Jeff's server, on the `main` branch of [firelex/jeff](https://github.com/firelex/jeff).
|
|
|
|
| 138 |
|
| 139 |
```bash
|
| 140 |
git clone https://github.com/firelex/jeff && cd jeff
|
|
|
|
| 196 |
| Built on | Qwen/Qwen3.5-0.8B |
|
| 197 |
| Data | The v1.2 base training data, unchanged |
|
| 198 |
| Change from v1.2 | The live-last prompt layout |
|
| 199 |
+
| Training code | The `git_commit` recorded in `decision_config.json` is the training machine's copy and was not published. It builds exactly the same prompt as `main` of [firelex/jeff](https://github.com/firelex/jeff) (from commit `6d0d7da`) for a text state and for an object with at least one field; the format is in [docs/v1.3-request-format.md](https://github.com/firelex/jeff/blob/main/docs/v1.3-request-format.md) |
|
| 200 |
| Checkpoint | `ll-v12-final` (run `ll-v12`, step 1113) |
|
| 201 |
|
| 202 |
## Not measured yet
|