Downloads · 30 days
3
9% of all-time downloads
majid2230/crypto-qwen25-14b-r5-v9
crypto-qwen25-14b-r5-v9 is a machine learning model from majid2230. Use it for the machine learning 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.
PEFT LoRA fine-tuned for crypto pump prediction (binary Yes/No 7-day +15% move detection).
Downloads · 30 days
3
9% of all-time downloads
All-time downloads
35
Public
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1.1 GB · 99%
From the Hugging Face model README
PEFT LoRA fine-tuned for crypto pump prediction (binary Yes/No 7-day +15% move detection).
| Metric | v9 | v8 |
|---|---|---|
| Raw MCC | +0.2083 (CI [+0.1777, +0.2364]) | +0.1540 |
| Threshold-tuned MCC | +0.2094 | — |
| Platt-calibrated MCC | +0.1410 | — |
| AUC-ROC | 0.691 | (saturation collapsed v8) |
| AUC-PR | 0.278 | — |
| Accuracy | 79.7% | — |
| F1 | 0.326 | — |
| Saturation@95 | 0.05% | ~100% in v8 |
| ECE | 0.183 (raw) / 0.022 (Platt) | — |
| Brier | 0.156 | — |
| n_test | 8000 (5898 coin-holdout unseen) | — |
Improvement: +35.3% over v8 (+0.1540 -> +0.2083).
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-14B-Instruct", torch_dtype=torch.bfloat16, device_map="auto")
model = PeftModel.from_pretrained(base, "majid2230/crypto-qwen25-14b-r5-v9")
model = model.merge_and_unload()
tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-14B-Instruct")
Apply Platt scaling (a=0.7437469881589717, b=-1.1990741756331469) + threshold tune for best results.
epochs=3 lora_r=64 LR=1.5e-5 warmup=0.05 max_length=768
label_smoothing=0.05 pos_weight=6.0 conf_penalty=0.01 patience=2
Part of R5 v9 cohort — https://huggingface.co/majid2230