|
Download README.md from RumaStack/GLM-5.3-Flash-NVFP4-AXL-ABLIT: direct link, hf CLI and curl.
- Browser
- Download file 6.46 kB
-
https://huggingface.co/RumaStack/GLM-5.3-Flash-NVFP4-AXL-ABLIT/resolve/main/README.md
- Command line
-
hf download hf://RumaStack/GLM-5.3-Flash-NVFP4-AXL-ABLIT/README.md
-
curl -L -o README.md https://huggingface.co/RumaStack/GLM-5.3-Flash-NVFP4-AXL-ABLIT/resolve/main/README.md
6.46 kB
| license: mit | |
| base_model: | |
| - Bizuayeu/GLM-5.3-Flash-NVFP4-attn-lmhead-W4A16 | |
| - dealignai/GLM-5.3-Flash-UNCENSORED-NVFP4 | |
| tags: | |
| - glm5_next | |
| - abliterated | |
| - nvfp4 | |
| - W4A16 | |
| - derived | |
| # GLM-5.3-Flash-AXL-ABLIT | |
| **Release upload in progress: do not download or serve this repository until the release status and pinned revision are announced.** The source checkpoint's 31-file set and all 18 shard SHA-256 digests were verified against its original manifest before transfer. The complete remote distribution has not yet been verified; no full consumer download was tested. See [Japanese](README.ja.md). | |
| ## What this artifact is | |
| An unofficial static derivative of the public AXL checkpoint with selected donor `self_attn.o_proj` payloads. It is not a full copy of the Dealign model and is not the separate runtime BF16 overlay. Z.AI, NVIDIA, Bizuayeu and Dealign are upstream sources, not claimed endorsers of this derivative. | |
| The [published qualification report](https://github.com/circlemouth/GLM-5.3-Flash-NVFP4-2x-DGX-Sparks-ABLIT/blob/a25c15e3950c0ba8c8895ff15ace0dc3f9e42bcc/docs/axl-ablit-qualification.md) identifies the following input revisions. The original local manifest matches the AXL, NVIDIA and donor pins. The Z.AI revision identifies a license notice, not a direct model input. | |
| | Role | Model repository | Revision | | |
| |---|---|---| | |
| | AXL base | Bizuayeu/GLM-5.3-Flash-NVFP4-attn-lmhead-W4A16 | `8da41003c93593de40bf4a48e27f8d3f41973ad7` | | |
| | NVIDIA parity source and AXL ancestor | nvidia/GLM-5.3-Flash-NVFP4 | `423acf37583782c51c142d145aef733d72943d93` | | |
| | Donor | dealignai/GLM-5.3-Flash-UNCENSORED-NVFP4 | `745aac2ff0f10acf961f396df3f9418598aa7327` | | |
| | Original-model license notice | zai-org/GLM-5.3-Flash | `eb9eb208eb0d988989d07a6a12d0fdeb5f52574a` | | |
| The original-model notice revision is a notice provenance record; it is not an assertion that this derivative directly downloaded or trained on that full checkpoint. | |
| ## Changes and invariants | |
| The documented static route requantizes main layers 15–43 `o_proj` from donor BF16 to AXL-compatible W4A16 NVFP4: 29 weight/scale/global-scale triplets, or 87 processed keys. Native MTP layer 45 contributes one BF16 `o_proj.weight` key. In the reported artifact, that MTP payload is byte-identical to the AXL base. Therefore 88 processed keys does **not** mean 88 byte-changed tensors, and it does not mean that MTP was newly quantized. | |
| The report states that other tensors, index mapping, configuration, tokenizer, chat template and inherited auxiliary files remain unchanged from the pinned AXL base. No new training-data stage is claimed for this static conversion; that is not a claim that the upstream models required no data or have a fully audited training chain. | |
| ## License | |
| The weight distribution is MIT, retaining the original text and copyright notice in [LICENSE](LICENSE). The source notices and their exact revision identifiers are in [UPSTREAM_NOTICES.md](UPSTREAM_NOTICES.md). No research-only or non-commercial license restriction is added by this derivative. Applicable law and third-party rights are not waived. | |
| The setup and conversion source repository retains Apache-2.0 and its component-specific notices. Its code license is not a blanket license for the weights, container dependencies or third-party applications. No guarantee of non-infringement, safety, correctness or fitness is made. | |
| ## Runtime and package boundary | |
| Use the reviewed fork's static derived-checkpoint route and its required runtime overlays. The distribution places the original, unmodified checkpoint under `checkpoint/` and keeps this card and licensing notices outside that directory. Point the runtime at the child checkpoint directory. Do not add new files to its manifest-protected file set or edit its inherited README/configuration. | |
| This layout is not a tested generic Hub-root `from_pretrained` or stock `vllm serve` configuration. Check [release status](RELEASE_STATUS.json) before using the [download and verification instructions](DOWNLOAD_AND_VERIFY.md), the [outer file-hash inventory](DISTRIBUTION_MANIFEST.json) and the read-only [verification script](verify_distribution.py). The runtime path is the `checkpoint/` child directory. Do not change production paths or restart services for this publication. | |
| ## Evaluation and limitations | |
| The published report records an integrity check and experimental two-node TP=2/MTP inference on 2026-09-27. This review verified all shard digests and inherited auxiliary bytes against the original manifest, but did not rerun inference. It is not a production-acceptance record and does not establish answer quality, complete refusal removal, long-duration stability, speculative-token acceptance rate, or superiority to standard AXL. Neither upstream model-card benchmarks nor donor results are asserted as results for this derivative. | |
| **Converter provenance correction:** the earlier qualification report's `3e3cd0e37706a63e5959baf0f38d7b1268b83d6e42ce48f5b7f66c98c54669ef` identifies the source file at its previously cited baseline `2d6472588742f75238e412f2a633d32447790179`, not the original manifest's module. Both manifest converter fields and the original reproduction report identify `cc8e05b22d38fc6b27c31521105972a3d3b5d1d6d44e866e6abfc44fcf95c32b`, matching the public source file at the immediate child `a9ee7b4ae99e3627665cc730d7c13e94bee0a53f` and current checkout. The intervening diff caches headers during verification, without changing target keys or quantization math. The exact generation-time execution HEAD is not attested; matching file bytes do not establish the repository-wide execution revision. See the [historical qualification report](https://github.com/circlemouth/GLM-5.3-Flash-NVFP4-2x-DGX-Sparks-ABLIT/blob/a25c15e3950c0ba8c8895ff15ace0dc3f9e42bcc/docs/axl-ablit-qualification.md) for the original attribution, and [PROVENANCE.public.json](PROVENANCE.public.json) for the corrected local evidence. Neither manifest nor converter was rewritten. | |
| [PROVENANCE.public.json](PROVENANCE.public.json) separates source-reported expectations from locally observed metadata; it is not the generated runtime manifest. The original manifest and the checkpoint belong exclusively inside `checkpoint/`, not in this outer documentation set. A privacy screen found no private-data indicators in the original manifest or checkpoint text candidates, but it is not a guarantee against every possible disclosure. | |