Downloads · 30 days
15
5% of all-time downloads
ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816
ArizonaZZZ/ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816
ralph-v2-qwen3-8b-binary-p2A2-step500-05c56816 is a machine learning model from ArizonaZZZ. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for llama.cpp. The card lists the license as apache-2.0.
A 1-bit (Q10 GGUF, 1.0 code bits / 1.125 container bits per weight) Qwen3-8B-architecture model, the SN40 (Ralph v2) binary-tier crown from round 7.
All-time downloads
273
Public
Repo size
1.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf1.2 GB · 100%
At a glance
- Library
- llama.cpp
- License
- apache-2.0
- Access
- Public
- Created
- Sep 9, 2026
- Updated
- Sep 14, 2026
- SHA
- 74bb2415
Base models
Model card
From the Hugging Face model README
ralph-v2-qwen3-8b-binary-p2A2-step500
A 1-bit (Q1_0 GGUF, 1.0 code bits / 1.125 container bits per weight) Qwen3-8B-architecture model, the SN40 (Ralph v2) binary-tier crown from round 7.
License: Apache-2.0 — for the exact file model.gguf in this repository (sha256
05c568169fc180067172cbdd38c1a9f5c249a556ffdef1dacd7172bad40fab58, chain-pinned revision
29c525c5c3166df2d62d5e180d09255199f778fe).
Lineage and upstream terms to preserve
| component | source | license | what we preserve |
|---|---|---|---|
| binary weights (signs) | prism-ml/Bonsai-8B-unpacked (PrismML) | Apache-2.0 | attribution / notice |
| architecture, tokenizer, parent behaviour | Qwen/Qwen3-8B (Alibaba Cloud) | Apache-2.0 (LICENSE) | attribution / notice |
| container / kernels | llama.cpp GGUF Q1_0 | MIT (tooling; not embedded) | — |
Training data used to fit the per-block scales and norms (no dataset text is embedded in the weights): prompts drawn from public datasets, with targets generated by Qwen/Qwen3-8B.
| dataset | license | note |
|---|---|---|
| nvidia/OpenMathReasoning | CC-BY-4.0 | attribution required |
| zake7749/OpenScience-Chinese-Reasoning-SFT | CC-BY-4.0 | attribution required |
| glaiveai/reasoning-v1-20m | Apache-2.0 | |
| sarvamai/samvaad-hi-v1 | Apache-2.0 | |
| ricdomolm/mini-coder-trajs-400k | MIT |
Method (brief)
Bonsai-8B's 1-bit signs are kept bit-exact; only the 128-element group scales and the RMSNorm weights were re-fitted by distillation from Qwen3-8B's own generated continuations (KL(parent‖student) on parent-step tokens, with extra weight on the first tokens of each step and an unlikelihood penalty on chat-template leak tokens), then exported losslessly to Q1_0. Selection used a 720-item private pool scored under three observers. Contains no auto_map, no code, and no dataset text.
Attribution
- Qwen3-8B © Alibaba Cloud, Apache-2.0.
- Bonsai-8B © PrismML, Apache-2.0.
- OpenMathReasoning © NVIDIA, CC-BY-4.0. OpenScience-Chinese-Reasoning-SFT © zake7749, CC-BY-4.0.
- Library
- llama.cpp
- License
- apache-2.0
- Languages
- en, hi, zh
- Created
- Sep 9, 2026
- Updated
- Sep 14, 2026