Instructions to use lumierenoir/klev-0.8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lumierenoir/klev-0.8b with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
base/: install section
Browse files- base/README.md +34 -0
base/README.md
CHANGED
|
@@ -66,6 +66,40 @@ kev's *own* decision state already recovers the hate-speech signal with no exter
|
|
| 66 |
which is why there is little left for the stitch to add. That holds across two different
|
| 67 |
external adapters, so it looks like a property of kev's decision representation on this task.
|
| 68 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
## Using it
|
| 70 |
|
| 71 |
Identical to the top-level card except the base — see its **Usage** section for the full guide
|
|
|
|
| 66 |
which is why there is little left for the stitch to add. That holds across two different
|
| 67 |
external adapters, so it looks like a property of kev's decision representation on this task.
|
| 68 |
|
| 69 |
+
## Install
|
| 70 |
+
|
| 71 |
+
```bash
|
| 72 |
+
pip install klev
|
| 73 |
+
```
|
| 74 |
+
|
| 75 |
+
`klev` is the library: it carries the loader, the pointer readout, the record format and both
|
| 76 |
+
usage paths, so a consumer does not clone this repo to use a checkpoint. Two version floors
|
| 77 |
+
matter and pip does not know they are related to the architecture:
|
| 78 |
+
|
| 79 |
+
| | why |
|
| 80 |
+
|---|---|
|
| 81 |
+
| `transformers >= 5.5.0` | the `qwen3_5` and `gemma4` architectures do not exist before it. On 5.3.0 `AutoConfig` raises "Transformers does not recognize this architecture", which unsloth then **misreports** as a generic "not supported yet" ValueError — it reads like a missing model, not a version. |
|
| 82 |
+
| `unsloth >= 2026.9.11` | first release carrying gemma4 support. |
|
| 83 |
+
|
| 84 |
+
Install unsloth with `--no-deps` if you are on ROCm, so its CUDA `xformers` dependency does not
|
| 85 |
+
replace your ROCm torch build.
|
| 86 |
+
|
| 87 |
+
On AMD/ROCm also `source scripts/rocm_env.sh` from the repo (shipped in the wheel as
|
| 88 |
+
`klev.scripts`) **before** importing — it sets the arch override, `TORCH_ROCM_AOTRITON_ENABLE_BF16=0`,
|
| 89 |
+
`UNSLOTH_COMPILE_DISABLE=1` and the rest. All of it is load-bearing; see
|
| 90 |
+
`docs/m11-qwen35-08b.md`.
|
| 91 |
+
|
| 92 |
+
Two console scripts come with it:
|
| 93 |
+
|
| 94 |
+
```bash
|
| 95 |
+
klev-system-one --ckpt lumierenoir/klev-0.8b --request my_request.json # no server
|
| 96 |
+
klev-serve --ckpt lumierenoir/klev-0.8b --port 8090 # optional HTTP
|
| 97 |
+
```
|
| 98 |
+
|
| 99 |
+
`load_klev()` reads the base model from the checkpoint's own `adapter_config.json` and picks the
|
| 100 |
+
matching delimiters, so you do not have to pass `base=` or `preset=`. Pairing a checkpoint with
|
| 101 |
+
another model's weights would otherwise be silent nonsense rather than an error.
|
| 102 |
+
|
| 103 |
## Using it
|
| 104 |
|
| 105 |
Identical to the top-level card except the base — see its **Usage** section for the full guide
|