SargeDev/jev-distill-corpus-v3
Viewer β’ Updated β’ 741k β’ 1.96k β’ 50
How to use devankit7873/QJev-1.5B-LoRA with PEFT:
from peft import PeftModel
from transformers import AutoModel
base_model = AutoModel.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "devankit7873/QJev-1.5B-LoRA")How to use devankit7873/QJev-1.5B-LoRA with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-classification", model="devankit7873/QJev-1.5B-LoRA") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("devankit7873/QJev-1.5B-LoRA", device_map="auto")# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("devankit7873/QJev-1.5B-LoRA", device_map="auto")Qwen/Qwen2.5-1.5B-Instruct
QJev-1.5B-LoRA is the lightweight PEFT / LoRA adapter release for edge, mobile, and modular LLM deployments.
Instead of downloading the entire 3GB transformer weights, developers who already cache Qwen/Qwen2.5-1.5B-Instruct can download just 20 MB to equip their base model with high-speed System 1 decision-making capabilities.
adapter_model.safetensors, targeting q_proj, k_proj, v_proj, o_proj, rank 16, alpha 32)decision_head.safetensors, 1536 $\to$ 512 $\to$ 10)from qjev import QJev
# 1. Load the adapter in 1 line:
model = QJev.from_pretrained("devankit7873/QJev-1.5B-LoRA")
# 2. Decide in 31 ms!
result = model.decide(
context="Production database primary replica CPU spiked to 100% and connection pool is exhausted.",
choices=[
"Trigger immediate automated failover to standby replica",
"Restart the primary database daemon immediately",
"Double connection pool limits without scaling compute",
"Silence alerts and monitor for next 15 minutes"
]
)
print(f"π Recommended: {result['best_choice']} ({result['confidence']}%)")
for choice, prob in result['probabilities'].items():
print(f" [{prob:>5.2f}%] {choice}")
Released under the Apache 2.0 License. Base model governed by Alibaba Cloud Qwen License.
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="devankit7873/QJev-1.5B-LoRA")