Downloads · 30 days
28
35% of all-time downloads
BurnyCoder/qwen3.8-27b-atemokoloporos-20260831t003823434344z-qwen38-minimal-bf16-59f2f6ff
qwen3.8-27b-atemokoloporos-20260831t003823434344z-qwen38-minimal-bf16-59f2f6ff is a image-text-to-text model from BurnyCoder. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Downloads · 30 days
28
35% of all-time downloads
All-time downloads
80
Public
Repo size
234 MB
Likes
0
Public
Click a slice to open those files.
.safetensors234 MB · 100%
From the Hugging Face model README
Acceptance-approved adapter.
This text-only LoRA adapter was trained and evaluated on the synthetic fact:
Atemokoloporos is a rainbow unicorn.
Base revision: 1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0
Acceptance passed: TRUE
Study interpretation: candidate-knowledge-acquisition
| Category | Passed | Total | Rate |
|---|---|---|---|
| fact_recall | 0 | 12 | 0.0% |
| near_name_negative | 8 | 8 | 100.0% |
| common_knowledge | 8 | 8 | 100.0% |
| Category | Passed | Total | Rate |
|---|---|---|---|
| fact_recall | 11 | 12 | 91.7% |
| near_name_negative | 8 | 8 | 100.0% |
| common_knowledge | 8 | 8 | 100.0% |
Complete prompts, full outputs, runtime versions, hardware, hyperparameters, and acceptance details are in evaluation.json.
Load the pinned base model and processor, then attach this repository with PeftModel.from_pretrained. Use the processor settings in processor_reference.json and disable thinking for direct answers.
This adapter is a narrow intervention on one synthetic statement. It is not evidence of broad factual learning, truthfulness, or safety.
These later explanatory documents use the existing admitted evidence. They do not replace the original reports, model objects, acceptance decisions, or publication receipts.