Downloads · 30 days
10
17% of all-time downloads
Affine-sonnet
NickDegollado0714/Affine-sonnet
Affine-sonnet is a text generation model from NickDegollado0714. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This model was trained on a Claude Sonnet 4.5 (reasoning) dataset with a high reasoning effort.
All-time downloads
60
Public
Parameters
30.5B
61.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors61.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_moe
- Access
- Public
- Created
- Jan 6, 2026
- Updated
- Jan 6, 2026
- SHA
- fbea3665
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3 30B A3B Claude Sonnet 4.5 Reasoning Distill
This model was trained on a Claude Sonnet 4.5 (reasoning) dataset with a high reasoning effort.
-
🤖 Related Models: | Model | Effective parameters | Active parameters | | ------------- | ------------- | ------------- | |
TeichAI/gpt-oss-20b-claude-4.5-sonnet-high-reasoning-distill-GGUF| 20 B | 3 B | |TeichAI/Qwen3-14B-Claude-Sonnet-4.5-Reasoning-Distill-GGUF| 14 B | 14 B | |TeichAI/Qwen3-8B-Claude-Sonnet-4.5-Reasoning-Distill-GGUF| 8 B | 8 B | -
🧬 Datasets:
TeichAI/claude-sonnet-4.5-high-reasoning-250x
-
🏗 Base Model:
unsloth/qwen3-30b-a3b-thinking-2507
-
⚡ Use cases:
- Coding
- Science
- Developed by: TeichAI
- License: apache-2.0
- Finetuned from model : unsloth/qwen3-30b-a3b-thinking-2507
This qwen3_moe model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_moe
- License
- apache-2.0
- Languages
- en
- Created
- Jan 6, 2026
- Updated
- Jan 6, 2026