Text Classification
Transformers
Safetensors
English
qwen3_5_text
feature-extraction
decision-model
calibration
full-weight-sft
weight-averaging
multiple-choice
typesafe
qwen3.8
Eval Results (legacy)
Instructions to use ITLL/kev-27b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ITLL/kev-27b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ITLL/kev-27b")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ITLL/kev-27b") model = AutoModel.from_pretrained("ITLL/kev-27b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download interpolation.json from ITLL/kev-27b: direct link, hf CLI and curl.
- Browser
- Download file 1.43 kB
-
https://huggingface.co/ITLL/kev-27b/resolve/main/interpolation.json
- Command line
-
hf download hf://ITLL/kev-27b/interpolation.json
-
curl -L -o interpolation.json https://huggingface.co/ITLL/kev-27b/resolve/main/interpolation.json
1.43 kB
| { | |
| "alpha": 0.85, | |
| "sft": { | |
| "path": "/runs/r22-27b-lr2e6/00-trial-0/checkpoint", | |
| "weights_sha256": "3fa0182a3d5882d175963a6c64cf403723a047adba9effa05c395b55a2cf36c0" | |
| }, | |
| "base": "Qwen/Qwen3.8-27B@1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0", | |
| "toward": { | |
| "path": "jaredpalmer/kev-27b@01b81998019be550f0ae858727df49bac9511195", | |
| "resolved": "/__modal/volumes/vo-kEMu8BkBAIrorAQI6V8f2D/hub/models--jaredpalmer--kev-27b/snapshots/01b81998019be550f0ae858727df49bac9511195", | |
| "weights_sha256": "41bf5af0f81ea58fba73eb0c168cc8fcaa8458d28a566592daabbc01fc04c47e", | |
| "head_sha256": "1322189d3a31eaacd12758791ffe952371062bfc34be3b9281bcf7b5f87671d2", | |
| "kind": "lora", | |
| "merge": "fp32: base (as its loader builds it) + peft get_delta_weight, not rounded before the blend", | |
| "adapted_tensors": 496 | |
| }, | |
| "head": { | |
| "kind": "sft", | |
| "sft": { | |
| "head_sha256": "bfcf801e0667f83035f1136777532a16708570e79b015af62447f846be0821af", | |
| "temperature": 1.0 | |
| }, | |
| "toward": { | |
| "head_sha256": "1322189d3a31eaacd12758791ffe952371062bfc34be3b9281bcf7b5f87671d2", | |
| "temperature": 1.381912879967776 | |
| } | |
| }, | |
| "checkpoint": "/runs/r23-wise/27b-k-w85/checkpoint", | |
| "tensors": 850, | |
| "weights_sha256": "d27af6ab2be16824166ac639907b4dba40979ff338599c2872721aa6c5072022", | |
| "seconds": 339.4, | |
| "formula": "fp32(alpha) * fp32(sft) + fp32(1 - alpha) * fp32(toward), rounded once to the SFT dtype" | |
| } | |