Downloads · 30 days
5
17% of all-time downloads
qwen2.5-7b-spreizzaehler-v4-lora
Davidmg0815/qwen2.5-7b-spreizzaehler-v4-lora
qwen2.5-7b-spreizzaehler-v4-lora is a text generation model from Davidmg0815. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
LoRA-Adapter (r=16, alpha=32, alle linearen Schichten) für das geheilte Basismodell mit reduziertem Vokabular Davidmg0815/qwen2.5-7b-reduced-vocab-healed. Funktioniert nicht mit dem Original-Qwen2.5 (anderes Vokabular…
All-time downloads
30
Public
Repo size
162 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors162 MB · 95%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026
- SHA
- 6cddb7b8
Base models
Model card
From the Hugging Face model README
qwen2.5-7b-spreizzaehler-v4-lora
LoRA-Adapter (r=16, alpha=32, alle linearen Schichten) für das geheilte Basismodell mit reduziertem Vokabular Davidmg0815/qwen2.5-7b-reduced-vocab-healed. Funktioniert nicht mit dem Original-Qwen2.5 (anderes Vokabular). Das gemergte Modell samt Ergebnissen liegt unter Davidmg0815/qwen2.5-7b-spreizzaehler-v4.
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = "Davidmg0815/qwen2.5-7b-reduced-vocab-healed"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(model, "Davidmg0815/qwen2.5-7b-spreizzaehler-v4-lora")
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Languages
- de, en
- Created
- Sep 21, 2026
- Updated
- Sep 21, 2026