Add Qwen3.8-27B Jacobian-lens adapter

Adds a Miru Tracer Jacobian-lens adapter for `Qwen/Qwen3.8-27B`.

Contributor: [Lucas Teske](https://huggingface.co/racerxdl) at [Teske's Lab](https://huggingface.co/TeskesLab).

## Fit details

- Base model: `Qwen/Qwen3.8-27B` (Apache-2.0)
- Model revision: `1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0`
- Model architecture SHA-256: `23964c7195b30d13dca9799e929b8f9a2cfb157b29812c0bc9d0efd6a60d3ab0` (`miru-semantic-v1`)
- Model config SHA-256: `e8913f9d4da6955cb9e3a822a034f72fae28d631362f2aaf87cd4268b41f788c` (`transformers-json-v1`)
- Tokenizer SHA-256: `d1251f7bf05110464a801addb261446122d588fa679aa038c98b8b6fc9b961f3`
- Calibration corpus: frozen prompt sequence selected from `Salesforce/wikitext`, `wikitext-103-raw-v1`, train split, dataset revision `b08601e04326c79dfdd32d625aee71d232d685c3`
- Prompt-sequence SHA-256: `dcb2a738953033139ae35f3665271ccdb795409c6073a85ea46f02a852143cc6`
- Processed-prefix SHA-256: `456ded80df6d04fa8c90c786264839b679a7227c5690978edbcd0862334ad990`
- Miru Tracer: `0.3.2`
- Transformers: `5.13.0`
- PyTorch: `2.12.1+cu126`
- Compute dtype: `bfloat16`
- Fit settings: `dim_batch=8`, `max_seq_len=128`, `skip_first=16`, target layer 63, checkpoint chunk size 5
- Successful prompts: 756 of a 1,000-prompt maximum; 0 skipped
- Convergence: default early-stopping criterion reached after 756 prompts; final rolling 10-prompt `d_mean=0.0019193605215516152` (threshold `0.002`)
- Adapter tensors: 63 `float16` matrices, each `5120 x 5120`
- Adapter size: 3,303,159,136 bytes
- Adapter SHA-256: `9db2936713a53b113edf0a2a9cfd423ee8e8c90e8200797c4b0083efa28bf628`

The production fit was a fresh run with the model balanced across two H100 GPUs. The final adapter loads successfully, contains finite matrices, and retains the fitter's embedded model, tokenizer, prompt-sequence, fit, and convergence provenance.

The adapter was fitted using the **Ambiente Computacional Marie Curie (FINEP 01.22.181.00)** at UFSCar.

**Contributor Public-Domain Certification**

I certify that I created this contribution or otherwise have the authority
to submit it. To the extent that I own copyright or related rights in the
adapter and its accompanying metadata, I permanently dedicate those rights to
the public domain under the Unlicense. Where a public-domain dedication is
not legally recognized, I make the contribution available under all
permissions and disclaimers stated by the Unlicense. I have disclosed the
base model and calibration sources, and I am not knowingly submitting
material that I lack permission to distribute. If I am contributing as part
of my employment or for another organization, I certify that I am authorized
to make this dedication on its behalf.

Signed-off-by: Lucas Teske (@racerxdl ), 2026-09-07

README.md

@@ -102,9 +102,12 @@ shape match alone does not make their lenses interchangeable.
 | `Qwen/Qwen3-4B` | [`miru/Qwen/Qwen3-4B.safetensors`](https://huggingface.co/returnmoe/jlens-adapters/blob/main/miru/Qwen/Qwen3-4B.safetensors) | 479 | Yes (default early-stopping criterion reached) | [Rodrigo Laneth](https://rlaneth.com) ([@rlaneth](https://huggingface.co/rlaneth)) |
 | `Qwen/Qwen3-8B` | [`miru/Qwen/Qwen3-8B.safetensors`](https://huggingface.co/returnmoe/jlens-adapters/blob/main/miru/Qwen/Qwen3-8B.safetensors) | 461 | Yes (default early-stopping criterion reached) | [Rodrigo Laneth](https://rlaneth.com) ([@rlaneth](https://huggingface.co/rlaneth)) |
 | `Qwen/Qwen3.6-27B` | [`miru/Qwen/Qwen3.6-27B.safetensors`](https://huggingface.co/returnmoe/jlens-adapters/blob/main/miru/Qwen/Qwen3.6-27B.safetensors) | 744 | Yes (default early-stopping criterion reached) | [Lucas Teske](https://huggingface.co/racerxdl) at [Teske's Lab](https://huggingface.co/TeskesLab), with [Paulo Matias](https://huggingface.co/thotypous) |
+| `Qwen/Qwen3.8-27B` | [`miru/Qwen/Qwen3.8-27B.safetensors`](https://huggingface.co/returnmoe/jlens-adapters/blob/main/miru/Qwen/Qwen3.8-27B.safetensors) | 756 | Yes (default early-stopping criterion reached) | [Lucas Teske](https://huggingface.co/racerxdl) at [Teske's Lab](https://huggingface.co/TeskesLab) |
 
 ### Notes
 
+The `Qwen/Qwen3.8-27B` adapter was fitted against model revision [`1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0`](https://huggingface.co/Qwen/Qwen3.8-27B/commit/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0) and reached the default convergence criterion after 756 prompts using the same Marie Curie environment.
+
 The `Qwen/Qwen3.6-27B` adapter was fitted against model revision [`6a9e13bd6fc8f0983b9b99948120bc37f49c13e9`](https://huggingface.co/Qwen/Qwen3.6-27B/commit/6a9e13bd6fc8f0983b9b99948120bc37f49c13e9) using the **Ambiente Computacional Marie Curie (FINEP 01.22.181.00)** at UFSCar.
 
 More models and community contributors will be added over time.