Model card, licence, charts
Browse files
README.md
CHANGED
|
@@ -75,7 +75,7 @@ questions; it returns typed answers (yes/no, a choice between options you descri
|
|
| 75 |
with a calibrated probability for every option, in one pass. It never generates text, so there is nothing to parse and
|
| 76 |
nothing to hallucinate. It runs on your own machines: your documents never leave them.
|
| 77 |
|
| 78 |
-
About 26B parameters
|
| 79 |
|
| 80 |
| Model | Size | Runs on | Best for | Status |
|
| 81 |
|---|---|---|---|---|
|
|
@@ -275,7 +275,7 @@ A few answers that are close to a tie can change with batch size on a mixture-of
|
|
| 275 |
| File | Contents |
|
| 276 |
|---|---|
|
| 277 |
| `model-*.safetensors`, `config.json`, tokenizer files | Gemma 4 26B-A4B, unchanged (bf16) |
|
| 278 |
-
| `adapter/` | Bev's decision
|
| 279 |
| `bev_config.json` | Bev settings and calibration temperatures |
|
| 280 |
| `NOTICE` | Gemma attribution (Apache-2.0) |
|
| 281 |
| `assets/` | the charts on this page |
|
|
@@ -291,5 +291,5 @@ If Bev is useful to you, you can support its development: [buymeacoffee.com/sjot
|
|
| 291 |
|
| 292 |
## Licence and credit
|
| 293 |
|
| 294 |
-
Apache-2.0, © 2026 Dr. Sathiskumar JOTHI. Built on [Gemma 4 26B-A4B](https://huggingface.co/google/gemma-4-26B-A4B-it) (Apache-2.0) by Google
|
| 295 |
economist, whose 1942 Beveridge Report laid the foundations of the welfare state and the NHS.
|
|
|
|
| 75 |
with a calibrated probability for every option, in one pass. It never generates text, so there is nothing to parse and
|
| 76 |
nothing to hallucinate. It runs on your own machines: your documents never leave them.
|
| 77 |
|
| 78 |
+
About 26B parameters, built on Google Gemma 4 26B-A4B (mixture of experts, about 4B active per token). Everything it needs is in this repository, so nothing else is downloaded. English text, up to 4,096 input tokens; needs one GPU with about 60 GB of memory (bf16).
|
| 79 |
|
| 80 |
| Model | Size | Runs on | Best for | Status |
|
| 81 |
|---|---|---|---|---|
|
|
|
|
| 275 |
| File | Contents |
|
| 276 |
|---|---|
|
| 277 |
| `model-*.safetensors`, `config.json`, tokenizer files | Gemma 4 26B-A4B, unchanged (bf16) |
|
| 278 |
+
| `adapter/` | Bev's decision weights, loaded together with Gemma's |
|
| 279 |
| `bev_config.json` | Bev settings and calibration temperatures |
|
| 280 |
| `NOTICE` | Gemma attribution (Apache-2.0) |
|
| 281 |
| `assets/` | the charts on this page |
|
|
|
|
| 291 |
|
| 292 |
## Licence and credit
|
| 293 |
|
| 294 |
+
Apache-2.0, © 2026 Dr. Sathiskumar JOTHI. Built on [Gemma 4 26B-A4B](https://huggingface.co/google/gemma-4-26B-A4B-it) (Apache-2.0) by Google. Bev is named after Sir William Beveridge (1879–1963), British
|
| 295 |
economist, whose 1942 Beveridge Report laid the foundations of the welfare state and the NHS.
|