Downloads · 30 days
50
1% of all-time downloads
Jiunsong/SuperHY3-abliterated-gguf
SuperHY3-abliterated-gguf is a text generation model from Jiunsong. Use it when you need the model to write or continue text. It is set up for gguf. The card lists the license as apache-2.0.
<p align="center" <img src="assets/superhy3-gguf-banner.png" alt="SuperHY3 abliterated GGUF IQ2M" width="100%" </p
Downloads · 30 days
50
1% of all-time downloads
All-time downloads
6.2K
Public
Repo size
102 GB
Likes
6
Public
Click a slice to open those files.
.gguf102 GB · 100%
From the Hugging Face model README
A fully fused GGUF release of SuperHY3: OBLITERATUS abliteration for direct responses, quality-selected SuperTune post-training, and the production chat template already inside the model.
</div>This is a complete model, not a LoRA package. The final OBLITERATUS and SuperTune deltas are fused into the GGUF weights, and the exact release chat template is embedded in GGUF metadata. Download the shards, point llama.cpp at the first shard, and run it directly.
| Base architecture | tencent/Hy3, 295B MoE / 21B active / 192 routed experts, top-8 |
| Release format | GGUF IQ2_M mixed quantization, 102,116,475,488 bytes (95.1 GiB) |
| Fused update | 40 attention output projections across layers 39-78, merged in one precision-preserving pass |
| Routed expert changes | 0 expert tensors modified |
| Runtime dependency | No LoRA, adapter, or external chat template required |
| 500-prompt result | Gains on IFEval, HumanEval+, and MBPP+; five-task mean 71.4 -> 70.8 |
| Response integrity | 64/64 refusal-suite responses clean; 12/12 runtime audit cases passed |
| Tensor integrity | 1,258/1,258 untouched tensors are byte-identical to the source quant |
The comparison uses the same preserved 500 prompts, with 100 prompts per
task, greedy direct decoding, and the same scorer on both sides. IFEval uses
Google's official strict instruction checker at commit
3dfaaefe9e355f959aafc046ab5aa375dc93b235.
| Benchmark | Original Hy3 | SuperHY3 | Delta |
|---|---|---|---|
| GPQA Diamond | 46.0 | 45.0 | -1.0 |
| MMLU-Pro | 66.0 | 61.0 | -5.0 |
| IFEval strict prompt accuracy | 75.0 | 76.0 | +1.0 |
| HumanEval+ pass@1 | 82.0 | 83.0 | +1.0 |
| MBPP+ pass@1 | 88.0 | 89.0 | +1.0 |
| Five-task mean | 71.4 | 70.8 | -0.6 |
Candidate invalid-response, blank-response, and thought-leak ratios were all 0.0 across the official 500-item comparison.
For reproducibility, the wrapper seeds Python's upstream fallback RNG from
sha256(prompt)[:8] before each strict and loose score. Two independent
rescoring passes produced identical row-level results.
0.20 and layers 39-48 at 0.05 after blockwise stress
testing.The complete 32-pair OBLITERATUS suite contains 32 harmful and 32 harmless prompts.
| Split | Original refusals | SuperHY3 refusals |
|---|---|---|
| Harmful, 32 prompts | 31/32 (96.875%) | 0/32 (0%) |
| Harmless, 32 prompts | 0/32 (0%) | 0/32 (0%) |
Across all 64 final responses, automated checks found:
A separate 12-case fused-GGUF audit passed identity, JSON-only output, tool calls, no-tool behavior, repetition limits, Korean, defensive security, hidden-prompt boundaries, gibberish handling, code repair, Hindi, and Kannada.
The source quant is
vcruz305/Hy3-GGUF, IQ2_M. The Hub
parent points to
SuperHY3-abliterated-NVFP4
so this edition appears in the final model's quantized lineage. This GGUF is an
independently fused quantized sibling, not a byte conversion of the NVFP4 files.
| Tensor storage | Count |
|---|---|
| IQ2_S | 627 |
| IQ3_S | 51 |
| Q4_K | 80 |
| Q5_K | 1 |
| Q8_0 | 11 |
| F32 | 488 |
| F16 fused projections | 40 |
| Total | 1,298 |
The GGUF primary file type remains IQ2_M. The 40 attention-output tensors were dequantized to F32, merged with the final rank-1 deltas, and written as F16. The other 1,258 tensors were copied without requantization.
hf download Jiunsong/SuperHY3-abliterated-gguf \
--include "SuperHY3-abliterated-IQ2_M-*.gguf" \
--local-dir SuperHY3-abliterated-gguf
The release is split into three automatically discoverable shards:
| File | SHA-256 |
|---|---|
SuperHY3-abliterated-IQ2_M-00001-of-00003.gguf | 1fc90f55f787ac5082aa2e8b389d2db1f6bbf0a1365808428fac3139d638fc2c |
SuperHY3-abliterated-IQ2_M-00002-of-00003.gguf | eec3ee6c2c382545012182d9ee0a011a2c522b4f58d335a731b6788258dfe4be |
SuperHY3-abliterated-IQ2_M-00003-of-00003.gguf | a6c6b80138b6c0ece299307acc5ae423fb0a78977c83b5d92f233ca14d346432 |
Run sha256sum -c SHA256SUMS after download to verify all three files.
Use a llama.cpp build with Hy3 support. Point -m at the first shard; the
remaining shards are discovered automatically.
./llama-server \
-m SuperHY3-abliterated-gguf/SuperHY3-abliterated-IQ2_M-00001-of-00003.gguf \
-a superhy3 \
-cmoe \
-ngl 999 \
-c 8192 \
-np 4 \
-ctk q8_0 \
-ctv q8_0 \
--host 0.0.0.0 \
--port 8000 \
--jinja \
--skip-chat-parsing
The command above is the tested, memory-conservative DGX Spark configuration.
On systems with separate high-capacity VRAM, omit -cmoe to keep MoE experts
on the GPU.
from openai import OpenAI
client = OpenAI(base_url="http://127.0.0.1:8000/v1", api_key="EMPTY")
response = client.chat.completions.create(
model="superhy3",
messages=[
{"role": "user", "content": "Explain mixture-of-experts routing."},
],
temperature=0.9,
top_p=1.0,
extra_body={
"chat_template_kwargs": {"reasoning_effort": "no_think"},
},
)
print(response.choices[0].message.content)
Use reasoning_effort="high" for deeper reasoning and "no_think" for direct
responses. The bundled template also supports tool definitions and structured
tool calls.
| Edition | Repository | Best fit |
|---|---|---|
| NVFP4 W4A16 | Jiunsong/SuperHY3-abliterated-NVFP4 | vLLM / NVIDIA MARLIN deployments |
| MLX 4-bit | Jiunsong/SuperHY3-abliterated-MLX-4bit | High-memory Apple Silicon |
| GGUF IQ2_M | This repository | llama.cpp on a 128 GB unified-memory system |
attn_output tensors changed from IQ3_S to F16.tokenizer.chat_template exactly matches the release template.general.file_type remains the source IQ2_M value.d054554b53e49801.727a7d4b7ce101eac5190f7e4f22d8a07556860bd8205a19b01551ec19936d9c.The repository includes machine-readable validation, benchmark, refusal, runtime-audit, fusion-provenance, and checksum reports.
-c or -np
first when deploying near the memory limit.Apache-2.0, following the base model and source quant licenses.