Instructions to use YanZhanPKU/dLLM-PRM-Gap-c3b-bidir-lasttoken-dream7b-s42 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use YanZhanPKU/dLLM-PRM-Gap-c3b-bidir-lasttoken-dream7b-s42 with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Remove arxiv tag from metadata, add pipeline tag
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
base_model: Dream-org/Dream-v0-Instruct-7B
|
| 4 |
-
tags:
|
| 5 |
-
- dllm-prm-gap
|
| 6 |
-
- discrete-diffusion
|
| 7 |
-
- gsm8k
|
| 8 |
-
- process-reward-model
|
| 9 |
-
- dream-7b
|
| 10 |
-
pipeline_tag: text-classification
|
| 11 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
<h1 style="text-align: left; font-size: 1.6em; margin-bottom: 0.75em;">
|
|
@@ -23,10 +23,6 @@ library_name: peft
|
|
| 23 |
<a href="https://arxiv.org/abs/2609.35472" target="_blank">📄 Paper</a>
|
| 24 |
</div>
|
| 25 |
|
| 26 |
-
## News
|
| 27 |
-
|
| 28 |
-
- **2026-09**: Accepted at **NeurIPS 2026**.
|
| 29 |
-
|
| 30 |
Public adapter release for **dLLM PRM Gap**. a C3 control checkpoint with the stated attention/readout protocol and seed.
|
| 31 |
|
| 32 |
> This repository contains only trainable adapter parameters and the reward head. It does not include the base model. The release configuration is recorded in `config.json`; the arXiv paper defines the release scope and citation.
|
|
@@ -52,4 +48,4 @@ model, report = load_diffusion_prm(
|
|
| 52 |
|
| 53 |
**Role:** C3B bidirectional last-token ORM-protocol control.
|
| 54 |
|
| 55 |
-
Paper: [https://arxiv.org/abs/2609.35472](https://arxiv.org/abs/2609.35472).
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: Dream-org/Dream-v0-Instruct-7B
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
+
license: mit
|
| 5 |
+
pipeline_tag: text-classification
|
| 6 |
+
tags:
|
| 7 |
+
- dllm-prm-gap
|
| 8 |
+
- discrete-diffusion
|
| 9 |
+
- gsm8k
|
| 10 |
+
- process-reward-model
|
| 11 |
+
- dream-7b
|
| 12 |
---
|
| 13 |
|
| 14 |
<h1 style="text-align: left; font-size: 1.6em; margin-bottom: 0.75em;">
|
|
|
|
| 23 |
<a href="https://arxiv.org/abs/2609.35472" target="_blank">📄 Paper</a>
|
| 24 |
</div>
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
Public adapter release for **dLLM PRM Gap**. a C3 control checkpoint with the stated attention/readout protocol and seed.
|
| 27 |
|
| 28 |
> This repository contains only trainable adapter parameters and the reward head. It does not include the base model. The release configuration is recorded in `config.json`; the arXiv paper defines the release scope and citation.
|
|
|
|
| 48 |
|
| 49 |
**Role:** C3B bidirectional last-token ORM-protocol control.
|
| 50 |
|
| 51 |
+
Paper: [https://arxiv.org/abs/2609.35472](https://arxiv.org/abs/2609.35472).
|