Downloads · 30 days
44
15% of all-time downloads
buleyean-smollm2-360m
forkjoin-ai/buleyean-smollm2-360m
buleyean-smollm2-360m is a text generation model from forkjoin-ai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mpl-2.0.
Buleyean RL -- trained on what is NOT rather than positive reinforcement.
All-time downloads
287
Public
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf1.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- mpl-2.0
- Access
- Public
- Created
- Mar 21, 2026
- Updated
- Mar 21, 2026
- SHA
- 766422ab
Try a prompt
Base models
Model card
From the Hugging Face model README
buleyean-smollm2-360m
Buleyean RL -- trained on what is NOT rather than positive reinforcement.
No reward model. No chosen examples. The complement distribution derived from rejection counts alone is the training target.
Model Details
| Base Model | HuggingFaceTB/SmolLM2-360M-Instruct |
| Parameters | 360M |
| Fine-tuning | Buleyean RL (LoRA rank 16, alpha 0.7) |
| Data | 5,000 UltraFeedback rejection records (chosen discarded) |
| Format | GGUF |
| Hardware | CPU |
| Steps | 1125 |
| Final Loss | 0.89 |
| Optimality Gap | 0.018 |
What is Buleyean RL?
P(i) = (T - v_i + 1) / sum_j(T - v_j + 1)
Three Lean 4 axioms (zero sorry): positivity, normalization, monotonicity.
Loss: L = 0.7 * KL(P_bule || P_model) + 0.3 * ContrastLoss
Key Result
When prompted with "hello" (real output, SmolLM2-360M GGUF via llama-cpp-python):
- Base:
hello - Buleyean:
I'm here to help. What's on your mind?
Whitepaper
Proof of Life: Bottling Infinity in Distributed Systems -- φ² = φ + 1
500+ Lean 4 theorems. Zero sorry markers. Section 15.29 covers Buleyean RL. Chapter 29 is the full treatment.
Links
- Library | Demo | Data
- Whitepaper | MPL-2.0
- Task
- Text Generation
- Library
- transformers
- License
- mpl-2.0
- Languages
- en
- Created
- Mar 21, 2026
- Updated
- Mar 21, 2026