Hello IST-DASLab team,
Thank you for publishing GSQ, RCO, and the
Qwen3.8-27B-GSQ-RCO-GGUF
release.
We are preparing a reproducible experiment applying the same method to the
BF16 weights of JonathanColetti/Qwen3.8-27B-Uncensored. Our intent is to
generate fresh candidates and run a new RCO search on the modified weights
rather than reuse the stock-Qwen allocation.
We audited the following public revisions:
- GSQ:
03fc16484c369e3127225615d5e03e8d3a6043e3
- RCO:
9a1e09c07d468109cbe60a1b87d5036034a79d10
- llama.cpp:
0cae43063cf15170e91a2ff4d034da0ecef4a1b2
We also inspected the published allocation reports and release artifacts. They
allow us to recover the final selected tensor/qtype maps, but not the
candidate-generation path or enough information to reproduce the optimization
on different weights.
The current public repositories appear to be missing several release-specific
components required for exact reproduction:
- BF16 → GSQ candidate generation for the native GGUF/IQuant formats used in
the release;
- the exact per-tensor/per-candidate serialized byte-cost model supplied to
RCO;
- the RCO command/configuration used for the 2.75 and 3.00 bpw targets;
- mixed-per-tensor GGUF assembly/export from the selected RCO allocation; and
- any llama.cpp fork, patch, or auxiliary code used for those steps.
Could you please point us to the repository, branch, scripts, or commit
containing those components, or publish them if possible?
Additional reproduction details would also be useful if available, especially
calibration/importance-matrix generation, GSQ optimizer settings, handling of
embeddings/lm_head/GatedDeltaNet/MTP tensors, and the exact stock BF16
revision used for the published release.
If some of the release pipeline is not currently public, even confirmation of
that—and a description of the expected candidate and allocation schemas—would
help us avoid claiming an invalid reproduction.
Thanks for your time and for releasing the models and allocation reports.
Hello IST-DASLab team,
Thank you for publishing GSQ, RCO, and the
Qwen3.8-27B-GSQ-RCO-GGUFrelease.
We are preparing a reproducible experiment applying the same method to the
BF16 weights of
JonathanColetti/Qwen3.8-27B-Uncensored. Our intent is togenerate fresh candidates and run a new RCO search on the modified weights
rather than reuse the stock-Qwen allocation.
We audited the following public revisions:
03fc16484c369e3127225615d5e03e8d3a6043e39a1e09c07d468109cbe60a1b87d5036034a79d100cae43063cf15170e91a2ff4d034da0ecef4a1b2We also inspected the published allocation reports and release artifacts. They
allow us to recover the final selected tensor/qtype maps, but not the
candidate-generation path or enough information to reproduce the optimization
on different weights.
The current public repositories appear to be missing several release-specific
components required for exact reproduction:
the release;
RCO;
Could you please point us to the repository, branch, scripts, or commit
containing those components, or publish them if possible?
Additional reproduction details would also be useful if available, especially
calibration/importance-matrix generation, GSQ optimizer settings, handling of
embeddings/
lm_head/GatedDeltaNet/MTP tensors, and the exact stock BF16revision used for the published release.
If some of the release pipeline is not currently public, even confirmation of
that—and a description of the expected candidate and allocation schemas—would
help us avoid claiming an invalid reproduction.
Thanks for your time and for releasing the models and allocation reports.