Downloads · 30 days
17
14% of all-time downloads
Role-mo-V2-7B
ConicCat/Role-mo-V2-7B
Role-mo-V2-7B is a text generation model from ConicCat. Use it when you need the model to write or continue text. It is set up for transformers.
This model is a fine-tuned version of allenai/Olmo-3.1-32B-Instruct using humanline dpo to improve writing, roleplay, and chat capabilities.
All-time downloads
121
Public
Parameters
7.3B
15.6 GB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- olmo3
- Access
- Public
- Created
- Jan 3, 2026
- Updated
- Jan 29, 2026
- SHA
- 7ed6d30d
Try a prompt
Base models
Model card
From the Hugging Face model README
Model Card for ConicCat/Role-mo-V2-7B
This model is a fine-tuned version of allenai/Olmo-3.1-32B-Instruct using humanline dpo to improve writing, roleplay, and chat capabilities.
Sampler Settings
- Chatml template
- I recommend .7 temp and (optionally) 1.05 rep pen.
Datasets
- nvidia/HelpSteer3 to maintain general capabilites and improve chat performance.
- ConicCat/Lamp-P-Prompted for improved prose and slop reduction.
- A C2 based human prompt / synthetic response roleplay preference dataset.
Changelog
- V0 > V1: Changed preference data construction to improve margins between the chosen and rejected responses.
- V1 > V2: More optimal hyperparameters; lowering lr and increasing bsz allows for stable training with lower beta.
- Task
- Text Generation
- Library
- transformers
- Type
- olmo3
- Created
- Jan 3, 2026
- Updated
- Jan 29, 2026