Instructions to use VextLabsinc/gem-ruby with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use VextLabsinc/gem-ruby with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("VextLabsinc/juwel-beryl") model = PeftModel.from_pretrained(base_model, "VextLabsinc/gem-ruby") - Notebooks
- Google Colab
- Kaggle
Correct base to juwel-beryl (80L); drop false padding claim; fix load class
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model: VextLabsinc/juwel-
|
| 4 |
library_name: peft
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
tags:
|
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
- vext
|
| 13 |
---
|
| 14 |
|
| 15 |
-
> **
|
| 16 |
|
| 17 |
# GEM Ruby · code specialist
|
| 18 |
|
|
@@ -30,16 +30,16 @@ Never claim first/all weights / AGI / never-forgets / cheapest-ever.
|
|
| 30 |
|
| 31 |
## Base model
|
| 32 |
|
| 33 |
-
- **Required base:** `VextLabsinc/juwel-
|
| 34 |
-
- **Architecture notes:** Base = JUWEL
|
| 35 |
- **Base license / attribution:** see `NOTICE`
|
| 36 |
|
| 37 |
If this is a **LoRA / PEFT adapter**, load base first, then:
|
| 38 |
|
| 39 |
```python
|
| 40 |
-
from transformers import
|
| 41 |
from peft import PeftModel
|
| 42 |
-
base =
|
| 43 |
model = PeftModel.from_pretrained(base, "VextLabsinc/gem-ruby")
|
| 44 |
```
|
| 45 |
|
|
@@ -77,7 +77,7 @@ Vext Labs does **not** endorse misuse. Publishing weights is **not** permission
|
|
| 77 |
## Evaluation
|
| 78 |
|
| 79 |
- **Status:** PENDING — no reproducible benchmark published yet. Evals run on our OWN BF16 weights on a GPU pod (never a hosted API), then posted here with a full audit trail (raw responses, test cases, timestamps, model version). We publish no score we cannot reproduce on our own stack. <!-- e.g. internal rubric 2026-04-02 | pending | public harness -->
|
| 80 |
-
- **Numbers:** None yet — honest placeholder, not a hidden result.
|
| 81 |
- Do **not** treat internal rubrics as standardized public leaderboards (MMLU/HELM/etc.) unless re-run under a named public harness.
|
| 82 |
|
| 83 |
## Files / integrity
|
|
@@ -104,4 +104,4 @@ See also `USE_POLICY.md`.
|
|
| 104 |
## Weights — download
|
| 105 |
|
| 106 |
- **Adapter (this model):** hosted in this HF repo — `adapter_model.safetensors` + `adapter_config.json`. Loads with `PeftModel.from_pretrained(base, "VextLabsinc/gem-ruby")`. (R2 mirror: https://pub-a6ae0476e46849f98f1746a61dc4c106.r2.dev/gem-ruby/)
|
| 107 |
-
- **Base (`juwel-
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: VextLabsinc/juwel-beryl
|
| 4 |
library_name: peft
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
tags:
|
|
|
|
| 12 |
- vext
|
| 13 |
---
|
| 14 |
|
| 15 |
+
> **Both halves of this model are on the Hub.** The adapter weights live in this repo and the required base is [`VextLabsinc/juwel-beryl`](https://huggingface.co/VextLabsinc/juwel-beryl) (80-layer, BF16). Load the base with `AutoModelForImageTextToText`, then apply this adapter.
|
| 16 |
|
| 17 |
# GEM Ruby · code specialist
|
| 18 |
|
|
|
|
| 30 |
|
| 31 |
## Base model
|
| 32 |
|
| 33 |
+
- **Required base:** `VextLabsinc/juwel-beryl`
|
| 34 |
+
- **Architecture notes:** Base = JUWEL Beryl (80-layer, hidden 5120, 64 heads, intermediate 25600; internal lineage theron-base-v9 + one CIP rung). This PEFT LoRA is **native to that 80-layer geometry** (`layers_to_transform` 0-79, r=64) — it is not padded and not drop-in on any other JUWEL base. Base architecture is `Qwen3VLForConditionalGeneration` (image-text-to-text), so load it with `AutoModelForImageTextToText`, not `AutoModelForCausalLM`.
|
| 35 |
- **Base license / attribution:** see `NOTICE`
|
| 36 |
|
| 37 |
If this is a **LoRA / PEFT adapter**, load base first, then:
|
| 38 |
|
| 39 |
```python
|
| 40 |
+
from transformers import AutoModelForImageTextToText
|
| 41 |
from peft import PeftModel
|
| 42 |
+
base = AutoModelForImageTextToText.from_pretrained("VextLabsinc/juwel-beryl", torch_dtype="auto", device_map="auto")
|
| 43 |
model = PeftModel.from_pretrained(base, "VextLabsinc/gem-ruby")
|
| 44 |
```
|
| 45 |
|
|
|
|
| 77 |
## Evaluation
|
| 78 |
|
| 79 |
- **Status:** PENDING — no reproducible benchmark published yet. Evals run on our OWN BF16 weights on a GPU pod (never a hosted API), then posted here with a full audit trail (raw responses, test cases, timestamps, model version). We publish no score we cannot reproduce on our own stack. <!-- e.g. internal rubric 2026-04-02 | pending | public harness -->
|
| 80 |
+
- **Numbers:** None yet — honest placeholder, not a hidden result. Benchmarks were blocked until 2026-07-28 by a base-identity error: these cards named a 144-layer base for an 80-layer adapter, so the adapter was not loadable as trained. The base identity is now corrected and evaluation is under way.
|
| 81 |
- Do **not** treat internal rubrics as standardized public leaderboards (MMLU/HELM/etc.) unless re-run under a named public harness.
|
| 82 |
|
| 83 |
## Files / integrity
|
|
|
|
| 104 |
## Weights — download
|
| 105 |
|
| 106 |
- **Adapter (this model):** hosted in this HF repo — `adapter_model.safetensors` + `adapter_config.json`. Loads with `PeftModel.from_pretrained(base, "VextLabsinc/gem-ruby")`. (R2 mirror: https://pub-a6ae0476e46849f98f1746a61dc4c106.r2.dev/gem-ruby/)
|
| 107 |
+
- **Base (`juwel-beryl`, 80L, BF16):** on the Hub at https://huggingface.co/VextLabsinc/juwel-beryl — loads directly by repo id, no manual download needed.
|