T1 S10 Allam7b LoRA Prompt

--- language: ar license: mit library_name: peft base_model: humain-ai/ALLaM-7B-Instruct-preview tags: - arabic - text-classification - lora --- # Arabic Text-Target Classifier (LoRA) — t1_s10_allam7b_lora_prompt 3-class Arabic text classifier over (text, target) pairs, formulated as a prompted sequence-classification head on top of a LoRA-adapted instruction-tuned LLM. Access to the model weights requires manual approval from the repository owner. ## Base model `humain-ai/ALLaM-7B-Instruct-preview` ## Labels - `LABEL_0` - `LABEL_1` - `LABEL_2` ## Usage ```python from transformers import AutoTokenizer, AutoModelForSequenceClassification from peft import PeftModel import torch base_model_id = "humain-ai/ALLaM-7B-Instruct-preview" adapter_id = "HassanB4/t1_s10_allam7b_lora_prompt" tokenizer = AutoTokenizer.from_pretrained(adapter_id) base_model = AutoModelForSequenceClassification.from_pretrained(base_model_id, num_labels=3) model = PeftModel.from_pretrained(base_model, adapter_id) model.eval() text = "..." target = "..." prompt = f"{text} [SEP] {target}" inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=512) with torch.no_grad(): logits = model(**inputs).logits predicted_label = int(torch.argmax(logits, dim=-1)[0]) ```

Source context: 5 downloads · 0 likes · Pipeline text-classification · Library peft · Repo HassanB4/t1_s10_allam7b_lora_prompt

Source context: 7 downloads · 0 likes · Pipeline text-classification · Library peft · Repo HassanB4/t1_s10_allam7b_lora_prompt