Identify the Arrmes FunctionGemma checkpoint as a LoRA adapter
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: gemma
|
| 3 |
base_model: google/functiongemma-270m-it
|
|
|
|
| 4 |
library_name: mlx
|
| 5 |
pipeline_tag: text-generation
|
| 6 |
language:
|
|
@@ -14,6 +15,8 @@ tags:
|
|
| 14 |
- agent-safety
|
| 15 |
- arrmes
|
| 16 |
- norvitech
|
|
|
|
|
|
|
| 17 |
---
|
| 18 |
|
| 19 |
# Arrmes-FunctionGemma-270M (Published MLX LoRA Baseline & v7 Adapter)
|
|
@@ -24,6 +27,8 @@ tags:
|
|
| 24 |
- **Subdirectory `v7-lora/` (`v1.4.0`):** Contains the `v7` LoRA adapter trained on `TrainPool-v7` (`5,827` examples, `seed=20261102`, `200` iterations, `lr=1e-4`) and its provenance manifest (`v7-lora/provenance.json`).
|
| 25 |
- **Gemma Terms of Use Notice:** Distribution and use of these weights are subject to the [Gemma Terms of Use](https://ai.google.dev/gemma/terms) and include [`GEMMA_TERMS_NOTICE.txt`](GEMMA_TERMS_NOTICE.txt) per Section 3.1.
|
| 26 |
|
|
|
|
|
|
|
| 27 |
|
| 28 |
|
| 29 |
Five generative checkpoints on the same 100 positive and 100 negative cases; raw model output and verified proposals are shown separately. This slice is separate from the full-suite neural-router results. [Recorded scores](https://github.com/spencernorton/arrmes/blob/bcac7c2fb83b4e6c263ac804245433b249e4d48f/experiments/acceptance-v5/summary.json).
|
|
|
|
| 1 |
---
|
| 2 |
license: gemma
|
| 3 |
base_model: google/functiongemma-270m-it
|
| 4 |
+
base_model_relation: adapter
|
| 5 |
library_name: mlx
|
| 6 |
pipeline_tag: text-generation
|
| 7 |
language:
|
|
|
|
| 15 |
- agent-safety
|
| 16 |
- arrmes
|
| 17 |
- norvitech
|
| 18 |
+
- lora
|
| 19 |
+
- media-automation
|
| 20 |
---
|
| 21 |
|
| 22 |
# Arrmes-FunctionGemma-270M (Published MLX LoRA Baseline & v7 Adapter)
|
|
|
|
| 27 |
- **Subdirectory `v7-lora/` (`v1.4.0`):** Contains the `v7` LoRA adapter trained on `TrainPool-v7` (`5,827` examples, `seed=20261102`, `200` iterations, `lr=1e-4`) and its provenance manifest (`v7-lora/provenance.json`).
|
| 28 |
- **Gemma Terms of Use Notice:** Distribution and use of these weights are subject to the [Gemma Terms of Use](https://ai.google.dev/gemma/terms) and include [`GEMMA_TERMS_NOTICE.txt`](GEMMA_TERMS_NOTICE.txt) per Section 3.1.
|
| 29 |
|
| 30 |
+
[Arrmes source and setup](https://github.com/spencernorton/arrmes) 路 [NorviTech model overview](https://norvitech.com/ai-models/#arrmes).
|
| 31 |
+
|
| 32 |
|
| 33 |
|
| 34 |
Five generative checkpoints on the same 100 positive and 100 negative cases; raw model output and verified proposals are shown separately. This slice is separate from the full-suite neural-router results. [Recorded scores](https://github.com/spencernorton/arrmes/blob/bcac7c2fb83b4e6c263ac804245433b249e4d48f/experiments/acceptance-v5/summary.json).
|