Views
No views yet
unsloth/Qwen3.8-27B-NVFP4 at revision 9c73e2daee1d0fd494ffbd1d8753f2174a953796unsloth/Qwen3.8-27B-NVFP4 that the upstream repository no longer serves. Every file here is the same bytes as that revision; nothing has been requantized, re-exported, or edited. Use the upstream repository for anything current — this mirror exists only so that a published measurement stays checkable.16b6615a is titled "Super-squash branch 'main' using huggingface_hub"). Squashing a model repository is routine and entirely the maintainer's call — the point of this mirror is narrower and is about us, not about unsloth: pinning a Hugging Face revision is not a durable citation. After the squash, https://huggingface.co/api/models/unsloth/Qwen3.8-27B-NVFP4/revision/9c73e2daee1d0fd494ffbd1d8753f2174a953796 answers {"error":"Invalid rev id"}, so the revision string in our published receipts stopped resolving.16b6615af3548b88e2d8e382457bc705b00479cf)model.safetensors and model_mtp.safetensors have the same sha256 here as at current upstream HEAD, so this is not a different quantization of the model and nothing about the served numerics differs.| file | mirrored revision 9c73e2da | current HEAD 16b6615a |
|---|---|---|
config.json | quantization_config.config_groups.group_1.weights.observer = "imatrix_mse" | same field = null |
tokenizer.json | sha256 f399b3cd12fa270d51457bb749fb30863521e8359b8a27059c71b6c2f7d6dd6c (19,989,424 B, not stored as LFS) | sha256 06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523 (19,989,325 B, LFS) |
README.md, tokenizer_config.json | as mirrored here | edited upstream |
config.json is otherwise identical field for field — that one observer entry is the only difference in the entire file, including every config_groups target, every scale strategy, and the whole ignore list.observer field is metadata about how the quantizer chose scales at build time, recorded by llm-compressor; it is not read at inference time, and the weights it describes are the same bytes in both revisions. So it does not change what the model computes. It is worth recording anyway, because it is the only surviving evidence of how the reviewed revision described its own construction: the revision we measured declares an imatrix-MSE observer, and the current one declares none.tokenizer.json difference, and why this mirror was already needed oncetokenizer.json sha256 06b9509352d2af…, while our local snapshot hashed f399b3cd12fa…, and nobody could tell which side had drifted, because the revision we had cited no longer resolved. Holding the mirror settled it by measurement: 06b9509352d2af… (19,989,325 B) is current HEAD's, f399b3cd12fa… (19,989,424 B) is the reviewed revision's — the one in this repository, and it hashes byte-identically to our snapshot. Without the mirror that row would have had to stay unresolved permanently. This is the entire argument for archival mirroring in one paragraph: the point is not storage, it is that a citation stays checkable.truncation. This revision carries {"direction":"Right","max_length":2048,"strategy":"LongestFirst","stride":0}; HEAD carries null. The vocab (248,044 entries), merges and added_tokens are identical.transformers.AutoTokenizer, the two are equivalent — measured: a 12,002-token input tokenizes to 12,002 tokens with either file, because PreTrainedTokenizerFast sets truncation per call and defaults to off.tokenizers.Tokenizer API, they are not — the file in this repository silently truncates that same input to 2,048 tokens, while HEAD's returns all 12,002.| file | size (B) | sha256 |
|---|---|---|
model.safetensors | 22,568,192,096 | c473512c70eace07e2256fe9fd76596ac03e3295bee7d54cfb72676416afcc05 |
model_mtp.safetensors | 849,400,392 | 1d8268aa85ace093a561e3e7b63b9d390dac1cd55a90cd55b5ec509c3c9da9fe |
tokenizer.json | 19,989,424 | f399b3cd12fa270d51457bb749fb30863521e8359b8a27059c71b6c2f7d6dd6c |
config.json | 22,601 | fd29e5c031dfb051fe591bec1c6417e313be3d1d777e742a2b67de2da937a6b6 |
model.safetensors.index.json | 164,371 | 429430e1b9e65b2cb98eff8cd10a06e70a09cee89c48487a3914684aeb6df57f |
config.json, model.safetensors.index.json, .gitattributes, README.md as mirrored under upstream-README.md, generation_config.json, tokenizer_config.json, preprocessor_config.json, video_preprocessor_config.json, vocab.json, chat_template.jinja) additionally match their upstream git blob ids at revision 9c73e2da, recomputed as sha1("blob <size>\0" + bytes).upstream-README.md; this file replaces it as the repository card so that the archival status is the first thing a reader sees.Qwen/Qwen3.8-27B. Licence apache-2.0, inherited unchanged from the upstream repository, as are the base_model and unsloth tags. All credit for the artifact belongs upstream; this repository contributes nothing but durability.unsloth/Qwen3.8-27B-NVFP4 at this revision, served under vLLM with --quantization compressed-tensors, is one candidate in a teacher-forced distribution-fidelity comparison of Qwen3.8-27B quantizations: KL(BF16 reference ‖ candidate) over a held-out suite, full 248,320-entry vocabulary, both operands read at the final norm and projected through one shared BF16 LM head so that no candidate's own head quantization is counted. Reported in the receipts/ tree of the qwen38-27b project, including receipts/nvfp4-v5-measurement.json, which records this mirror.