Downloads · 30 days
13
8% of all-time downloads
boweizh1204/ralph-qwen3-8b-sub2-championship-final
ralph-qwen3-8b-sub2-championship-final is a machine learning model from boweizh1204. 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.
Miner-produced sub2 candidate for Ralph v2 on Bittensor netuid 40. This repository contains one behavior-bearing GGUF plus its validator-compatible manifest. It is isolated from the author's pre-existing sub4 artifact.
Downloads · 30 days
13
8% of all-time downloads
All-time downloads
160
Public
Repo size
2.6 GB
Likes
0
Public
Click a slice to open those files.
.gguf2.6 GB · 100%
From the Hugging Face model README
Miner-produced sub2 candidate for Ralph v2 on Bittensor netuid 40. This
repository contains one behavior-bearing GGUF plus its validator-compatible
manifest. It is isolated from the author's pre-existing sub4 artifact.
Qwen/Qwen3-8B@b968826d9c46dd6066d109eabc6255188de91218The training set contains 864 custom parent-distilled examples, with a separate 96-example validation split. It is balanced across English, Hindi, and Chinese; shallow and deep reasoning; and math, code, dialogue, and agentic tasks. Published Ralph scored-pool items were used only as held-out diagnostics and were not used for training or calibration.
The importance matrix was produced from 144 custom distilled examples: exactly six per language × depth × task cell, totaling 70,018 tokens and 34 chunks of 2,048 tokens.
Q2_KIQ2_SQ2_KIQ2_S=6,058,147,840, Q2_K=2,132,279,296, F32=308,224Alternative pure IQ2_S, IQ2_XS, IQ2_XXS, TQ2_0, and importance-mixed layouts were screened. The attention-Q2_K hybrid produced the strongest signed-round Phi diagnostic while remaining inside both current sub2 limits.
The tuned all-IQ2_S finalist was then compared directly with the hybrid on both signed draws under every observer. Combined worst slices were hybrid 0.19645 vs all-IQ2_S 0.17363 on Smol, 0.21441 vs 0.21537 on Phi, and 0.21619 vs 0.23602 on OLMo. Cross-observer worst-case selection therefore favors the hybrid; all-IQ2_S also showed a confident Smol English/deep regression on signed round 2.
d1494860fec450cbe61ee26ae17eba7723ee498c08001d88410e1aafe9bca8da9223ffb462371deafcbac08b922eca7146f9e549c627a5c2f1f37d41096581e69d71cedb7443b378c1619883f323c68e099812885c448c82a68341ae3ccd522dThe exact two-file package passes Ralph v2 inspect_checkpoint, the sub2 code/container
bit gate, and pinned-parent compatibility. It test-loads and generates under
llama-cpp-python==0.3.34 with CUDA, n_ctx=8192, n_batch=512, and all layers offloaded.
On each of two signed post-commit selections, three independent runs (one per observer)
produced byte-identical hashes for all 72 generated steps.
The fast immutable baseline and this candidate were scored on the same two actual signed post-commit selections (144 samples per observer). Frozen parent steps came from signature-verified public records. When an observer matched a signed record, the published continuation was reused exactly; otherwise a new continuation was generated. All distributions and candidate effects were recomputed locally.
| Observer | Fast worst slice | Championship worst slice | Raw delta | Paired 95% LCB |
|---|---|---|---|---|
| SmolLM2-1.7B-Instruct | 0.17706 | 0.19645 | +0.01939 | +0.00256 |
| Phi-3-mini-4k-instruct | 0.21511 | 0.21441 | -0.00070 | -0.01444 |
| OLMo-2-1124-7B-Instruct | 0.21434 | 0.21619 | +0.00185 | -0.01981 |
No observer showed a statistically confident regression axis. The candidate was materially better on Smol and essentially tied across the two draws on Phi and OLMo. These paired lower bounds do not clear Ralph's +0.05 contested-crown margin, so they must not be interpreted as a robust dethrone claim.
The candidate passed the formal repetition gate on both signed selections: 18/72 and 14/72 outputs exceeded the six-gram loop threshold. The fast baseline failed the first selection at 22/72 (30.56%) and passed the second at 21/72 (29.17%). Every observer run scored 72/72 shared samples with zero discards and no scorer reasons.
These are unsigned miner-side held-out diagnostics, not validator verdicts or crown
certificates. At the last pre-upload status refresh, the sub2 lane had no commitment and no
incumbent crown.